ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into feat/offline-gguf-export-vlm-7481-2214

Browse source
This commit is contained in:
Souravrajvi0 2026-07-27 08:33:46 +05:30 • committed by GitHub
commit d1692a0011
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
270 changed files with 21954 additions and 1916 deletions
Download patch file Download diff file Expand all files Collapse all files

58
.github/workflows/studio-backend-ci.yml vendored
View file

@ -30,6 +30,13 @@ on:
- 'unsloth/**'
- 'unsloth_cli/**'
- 'tests/**'
# The root installers: tests/sh/*.sh and tests/studio/install/* assert
# against these two files, so a change here must run the suite that
# covers it. Without them an install-only edit (the shape most AMD/ROCm
# routing fixes take) skipped Backend CI entirely.
- 'install.sh'
- 'install.ps1'
- 'scripts/**'
- 'pyproject.toml'
- '.github/workflows/studio-backend-ci.yml'
push:
@ -193,6 +200,7 @@ jobs:
--ignore=tests/sh \
--ignore=tests/studio/test_hardware_dispatch_matrix.py \
--ignore=tests/studio/test_is_mlx_dispatch_gate.py \
--ignore=tests/studio/test_xpu_spoof_pipeline.py \
--ignore=tests/vllm_compat \
--ignore=tests/version_compat \
-m 'not server and not e2e' \
@ -205,37 +213,43 @@ jobs:
env:
PYTHONPATH: ${{ github.workspace }}/studio
UNSLOTH_COMPILE_DISABLE: '1'
# These two files mutate hardware.py module globals at runtime
# via the spoof fixtures, which leaks state into any other test
# that imports hardware. Run them in their own pytest invocation
# so the leak does not cross file boundaries.
# These files mutate hardware.py module globals at runtime via the
# spoof fixtures (CUDA/ROCm/XPU/MLX/CPU), which leaks state into any
# other test that imports hardware. Run them in their own pytest
# invocation so the leak does not cross file boundaries.
run: |
python -m pytest -q --tb=short \
tests/studio/test_hardware_dispatch_matrix.py \
tests/studio/test_is_mlx_dispatch_gate.py
tests/studio/test_is_mlx_dispatch_gate.py \
tests/studio/test_xpu_spoof_pipeline.py
- name: Shell installer tests
# Subset that does not depend on a writable / pristine install.sh
# tree; test_install_host_defaults.sh checks install.ps1 layout
# which has drifted (separate followup).
# Auto-discovered rather than allowlisted. The old hardcoded list had
# silently fallen seven files behind tests/run_all.sh, including
# test_strixhalo_wsl_reroute.sh -- the only shell coverage of the ROCm
# WSL reroute -- so that suite never ran on a PR. Skips are explicit,
# each with a reason, and tests/studio/test_ci_shell_suite_coverage.py
# fails if this step stops discovering the directory or the skip list
# grows without one.
#
# Skipped:
# test_install_host_defaults.sh: asserts an install.ps1 layout that
# has drifted (separate followup).
# test_install_rollback_lifecycle.sh: already runs on both platforms
# in cross-platform-parity-ci.yml.
run: |
set -e
for s in \
tests/sh/test_get_torch_index_url.sh \
tests/sh/test_mac_intel_compat.sh \
tests/sh/test_node_decision.sh \
tests/sh/test_studio_home_node_dir.sh \
tests/sh/test_system_node_readonly.sh \
tests/sh/test_nvcc_meets_llama_minimum.sh \
tests/sh/test_resolve_cuda_archs.sh \
tests/sh/test_staged_validation_enabled.sh \
tests/sh/test_tauri_install_exit_order.sh \
tests/sh/test_torch_constraint.sh \
tests/sh/test_torch_flavor.sh \
tests/sh/test_with_llama_cpp_dir_flag.sh \
tests/sh/test_with_llama_cpp_dir_link_behavior.sh; do
skip="test_install_host_defaults.sh test_install_rollback_lifecycle.sh"
found=0
for s in tests/sh/test_*.sh; do
case " $skip " in
*" $(basename "$s") "*) echo "skipping $s (see workflow comment)"; continue ;;
esac
found=$((found + 1))
echo "::group::$s"
bash "$s"
echo "::endgroup::"
done
[ "$found" -gt 0 ] || { echo "::error::no shell tests discovered under tests/sh"; exit 1; }
echo "ran $found shell installer test files"

18
install.ps1
View file

@ -1917,12 +1917,14 @@ exit 0
# (gfx120X/110X/1151/1150/103X); unknown names fall back to CPU.
elseif ($ROCmGpuLabel) {
$nameArchTable = @(
@{ P = "9070 XT|9080"; A = "gfx1201" } # RDNA 4 (RX 9070 XT / 9080)
@{ P = "9070|9060"; A = "gfx1200" } # RDNA 4 (RX 9070 / 9060)
@{ P = "9070|9080"; A = "gfx1201" } # RDNA 4 (Navi 48: RX 9070 XT / 9070 GRE / 9070 / 9080)
@{ P = "9060"; A = "gfx1200" } # RDNA 4 (Navi 44: RX 9060 XT / 9060)
@{ P = "8065S|8060S|8050S|8040S|Strix Halo|Ryzen AI Max|AI Max"; A = "gfx1151" } # RDNA 3.5 (Strix Halo + Gorgon Halo: Radeon 8065S/8060S/8050S/8040S iGPU, Ryzen AI Max / Max+)
@{ P = "890M|880M|860M|840M|Strix Point|Krackan|HX 37[05]|AI 9 HX|AI 9 36[05]|AI 7 35[05]|AI 5 34[05]|AI 7 PRO 35|AI 5 33"; A = "gfx1150" } # RDNA 3.5 (Strix/Krackan Point: Radeon 890M/880M iGPU, Ryzen AI 9 HX 370/375)
@{ P = "RX 7900|RX 7800|RX 7700(?!S)|PRO W7900|PRO W7800|PRO W7700"; A = "gfx1100" } # RDNA 3 desktop/workstation (Navi 31)
@{ P = "RX 7600|RX 7700S|RX 7650|PRO W7600|PRO W7500|PRO V710"; A = "gfx1102" } # RDNA 3 (Navi 33)
@{ P = "890M|880M|Strix Point|HX 37[05]|AI 9 HX|AI 9 36[05]"; A = "gfx1150" } # RDNA 3.5 (Strix Point: Radeon 890M/880M, Ryzen AI 9 HX 370/375)
@{ P = "860M|840M|Krackan|AI 7 35[05]|AI 5 34[05]|AI 7 PRO 35|AI 5 33"; A = "gfx1152" } # RDNA 3.5 (Krackan Point: Radeon 860M/840M, Ryzen AI 7 350 / AI 5 340)
@{ P = "RX 7900|PRO W7900|PRO W7800"; A = "gfx1100" } # RDNA 3 desktop/workstation (Navi 31)
@{ P = "RX 7800|RX 7700(?!S)|PRO W7700|PRO V710"; A = "gfx1101" } # RDNA 3 (Navi 32)
@{ P = "RX 7600|RX 7700S|RX 7650|PRO W7600|PRO W7500"; A = "gfx1102" } # RDNA 3 (Navi 33)
@{ P = "780M|760M|740M|Phoenix|Hawk Point|Z1 Extreme|Z2 Extreme"; A = "gfx1103" } # RDNA 3 iGPU (Phoenix / Hawk Point)
@{ P = "RX 6900|RX 6800|RX 6750|RX 6700|PRO W6800|PRO W6900"; A = "gfx1030" } # RDNA 2 (Navi 21) -- gfx103X family
@{ P = "RX 6650|RX 6600|PRO W6600|PRO W6650"; A = "gfx1032" } # RDNA 2 (Navi 23) -- gfx103X family
@ -2203,6 +2205,7 @@ exit 0
$archFamilyMap = @{
"gfx1201" = "gfx120X-all"; "gfx1200" = "gfx120X-all" # RDNA 4
"gfx1151" = "gfx1151"; "gfx1150" = "gfx1150" # RDNA 3.5 (Strix Halo/Point)
"gfx1152" = "gfx1152" # RDNA 3.5 (Krackan Point)
"gfx1103" = "gfx110X-all"; "gfx1102" = "gfx110X-all" # RDNA 3
"gfx1101" = "gfx110X-all"; "gfx1100" = "gfx110X-all"
"gfx1036" = "gfx103X-all"; "gfx1035" = "gfx103X-all" # RDNA 2 (RX 6000)
@ -2224,6 +2227,7 @@ exit 0
$torchFloorMap = @{
"gfx1201" = "torch>=2.11.0,<2.12.0"; "gfx1200" = "torch>=2.11.0,<2.12.0"
"gfx1151" = "torch>=2.11.0,<2.12.0"; "gfx1150" = "torch>=2.11.0,<2.12.0"
"gfx1152" = "torch>=2.11.0,<2.12.0"
}
# Companion ranges track the torch ceiling so pip resolves a consistent
# trio on AMD's per-arch index (each published independently). Mirrors
@ -2231,10 +2235,12 @@ exit 0
$torchvisionFloorMap = @{
"gfx1201" = "torchvision>=0.26.0,<0.27.0"; "gfx1200" = "torchvision>=0.26.0,<0.27.0"
"gfx1151" = "torchvision>=0.26.0,<0.27.0"; "gfx1150" = "torchvision>=0.26.0,<0.27.0"
"gfx1152" = "torchvision>=0.26.0,<0.27.0"
}
$torchaudioFloorMap = @{
"gfx1201" = "torchaudio>=2.11.0,<2.12.0"; "gfx1200" = "torchaudio>=2.11.0,<2.12.0"
"gfx1151" = "torchaudio>=2.11.0,<2.12.0"; "gfx1150" = "torchaudio>=2.11.0,<2.12.0"
"gfx1152" = "torchaudio>=2.11.0,<2.12.0"
}
$archFamily = if ($ROCmGfxArch -and $archFamilyMap.ContainsKey($ROCmGfxArch)) { $archFamilyMap[$ROCmGfxArch] } else { $null }
if ($archFamily) {
@ -2264,7 +2270,7 @@ exit 0
$_pinRocm211 = ([int]$Matches[1] -eq 7 -and [int]$Matches[2] -eq 2)
}
# Only the 2.11-allowlist gfx arches need the floor; others publish <2.11 and stay bare.
$_pinGfx211 = @('gfx120x-all', 'gfx1151', 'gfx1150') -contains $_pinLeaf
$_pinGfx211 = @('gfx120x-all', 'gfx1151', 'gfx1150', 'gfx1152') -contains $_pinLeaf
if ($_pinGfx211 -or $_pinRocm211) {
$ROCmIndexUrl = $TorchIndexUrl
$ROCmTorchFloor = "torch>=2.11.0,<2.12.0"

121
install.sh
View file

@ -655,6 +655,15 @@ _apt_distro_description() {
)
}
# ── Helper: can the controlling terminal actually be opened for reading? ──
# `test -r` only checks permission bits, which look fine in containers and
# systemd units where open() then fails with ENXIO. Probe with a real open.
# The subshell is required: in dash a failed redirection on the special
# builtin `:` exits the whole script.
_can_read_tty() {
( : </dev/tty ) >/dev/null 2>&1
}
# ── Helper: install packages via apt, escalating to sudo only if needed ──
# Usage: _smart_apt_install pkg1 pkg2 pkg3 ...
_smart_apt_install() {
@ -695,24 +704,63 @@ _smart_apt_install() {
echo " from your distro's official repositories (not a third-party tarball)."
echo " !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
echo ""
printf " Accept? [Y/n] "
if [ -r /dev/tty ]; then
read -r REPLY </dev/tty || REPLY="y"
else
REPLY="y"
fi
case "$REPLY" in
[nN]*)
if _can_read_tty; then
printf " Accept? [Y/n] "
# The device opened, so a failed read is EOF, not consent: decline,
# as the autostart prompt below does. Enter is still yes (a
# successful read of an empty line).
read -r REPLY </dev/tty || REPLY="n"
case "$REPLY" in
[nN]*)
echo ""
echo " Please install these packages first, then re-run Unsloth Studio setup:"
echo " sudo apt-get update -y && sudo apt-get install -y $_STILL_MISSING"
exit 1
;;
esac
# Mirror the headless branch: on a sudoers denial, a wrong password
# or an apt error, say what to run by hand instead of letting set -e
# abort on a bare sudo/apt message.
if sudo apt-get update -y </dev/null &&
sudo apt-get install -y $_STILL_MISSING </dev/null; then
:
else
echo ""
echo " Please install these packages first, then re-run Unsloth Studio setup:"
echo " Could not install these packages: $_STILL_MISSING"
echo " See the error above."
echo " Please install them first, then re-run Unsloth Studio setup:"
echo " sudo apt-get update -y && sudo apt-get install -y $_STILL_MISSING"
exit 1
;;
*)
sudo apt-get update -y </dev/null
sudo apt-get install -y $_STILL_MISSING </dev/null
;;
esac
fi
else
# Nobody can answer a prompt or type a password here. -n makes sudo
# refuse rather than prompt into a closed stdin, which is how #7307
# died. Probe with the real commands: `sudo -l` answers whether they
# are *authorized*, not whether running them needs authentication.
# -k ignores any cached timestamp, so only a real NOPASSWD rule gets
# through, not someone's sudo in another shell minutes ago. Per
# sudo(8), -k alongside a command ignores the cached credentials and
# "will not update" them, so other sessions keep theirs.
echo " No terminal to confirm on; trying passwordless sudo."
if sudo -n -k apt-get update -y </dev/null &&
sudo -n -k apt-get install -y $_STILL_MISSING </dev/null; then
echo " Installed with passwordless sudo."
else
echo ""
echo " Could not install these packages: $_STILL_MISSING"
echo " Detected ${_ad_desc}."
# Either sudo refused, or apt failed on a bad repo, dpkg lock or
# network outage. sudo exits 1 on an auth/config problem and
# when the command cannot be executed, but otherwise passes the
# command's own status through, so state both causes.
echo " Either sudo needs a password here, or apt-get itself"
echo " failed; see the error above. With no terminal to"
echo " authenticate on, this cannot be done unattended."
echo " Please install them first, then re-run Unsloth Studio setup:"
echo " sudo apt-get update -y && sudo apt-get install -y $_STILL_MISSING"
exit 1
fi
fi
else
echo ""
echo " sudo is not available on this system."
@ -2260,6 +2308,7 @@ _amd_arch_index_family_for_gfx() {
gfx1201|gfx1200) echo gfx120X-all ;;
gfx1151) echo gfx1151 ;;
gfx1150) echo gfx1150 ;;
gfx1152) echo gfx1152 ;;
gfx1103|gfx1102|gfx1101|gfx1100) echo gfx110X-all ;;
gfx1036|gfx1035|gfx1034|gfx1033|gfx1032|gfx1031|gfx1030) echo gfx103X-all ;;
gfx90a) echo gfx90a ;;
@ -2271,12 +2320,14 @@ _amd_arch_index_family_for_gfx() {
# Map a GPU marketing name to gfx arch (kept in sync with install.ps1 nameArchTable).
_infer_amd_gfx_arch_from_gpu_name() {
case "$1" in
*"9070 XT"*|*9080*) echo gfx1201 ;;
*9070*|*9060*) echo gfx1200 ;;
*9070*|*9080*) echo gfx1201 ;;
*9060*) echo gfx1200 ;;
*"8065S"*|*"8060S"*|*"8050S"*|*"8040S"*|*"Strix Halo"*|*"Ryzen AI Max"*|*"AI Max"*) echo gfx1151 ;;
*"890M"*|*"880M"*|*"860M"*|*"840M"*|*"Strix Point"*|*"Krackan"*|*"HX 37"*|*"AI 9 HX"*|*"AI 9 36"*|*"AI 7 35"*|*"AI 5 34"*|*"AI 7 PRO 35"*|*"AI 5 33"*) echo gfx1150 ;;
*"RX 7600"*|*"RX 7700S"*|*"RX 7650"*|*"PRO W7600"*|*"PRO W7500"*|*"PRO V710"*) echo gfx1102 ;;
*"RX 7900"*|*"RX 7800"*|*"RX 7700"*|*"PRO W7900"*|*"PRO W7800"*|*"PRO W7700"*) echo gfx1100 ;;
*"890M"*|*"880M"*|*"Strix Point"*|*"HX 37"*|*"AI 9 HX"*|*"AI 9 36"*) echo gfx1150 ;;
*"860M"*|*"840M"*|*"Krackan"*|*"AI 7 35"*|*"AI 5 34"*|*"AI 7 PRO 35"*|*"AI 5 33"*) echo gfx1152 ;;
*"RX 7600"*|*"RX 7700S"*|*"RX 7650"*|*"PRO W7600"*|*"PRO W7500"*) echo gfx1102 ;;
*"RX 7800"*|*"RX 7700"*|*"PRO W7700"*|*"PRO V710"*) echo gfx1101 ;;
*"RX 7900"*|*"PRO W7900"*|*"PRO W7800"*) echo gfx1100 ;;
*"780M"*|*"760M"*|*"740M"*|*"Phoenix"*|*"Hawk Point"*|*"Z1 Extreme"*|*"Z2 Extreme"*) echo gfx1103 ;;
*"RX 6900"*|*"RX 6800"*|*"RX 6750"*|*"RX 6700"*|*"PRO W6800"*|*"PRO W6900"*) echo gfx1030 ;;
*"RX 6650"*|*"RX 6600"*|*"PRO W6600"*|*"PRO W6650"*) echo gfx1032 ;;
@ -2316,10 +2367,14 @@ _infer_linux_amd_gfx_arch() {
echo gfx1151
return 0
fi
if [ -n "$_gpu_evidence" ] && grep -qiE '890M|880M|860M|840M|Strix Point|Krackan|HX 37[05]|AI 9 HX|AI 9 36[05]|AI 7 35[05]|AI 5 34[05]|AI 7 PRO 35|AI 5 33' /proc/cpuinfo 2>/dev/null; then
if [ -n "$_gpu_evidence" ] && grep -qiE '890M|880M|Strix Point|HX 37[05]|AI 9 HX|AI 9 36[05]' /proc/cpuinfo 2>/dev/null; then
echo gfx1150
return 0
fi
if [ -n "$_gpu_evidence" ] && grep -qiE '860M|840M|Krackan|AI 7 35[05]|AI 5 34[05]|AI 7 PRO 35|AI 5 33' /proc/cpuinfo 2>/dev/null; then
echo gfx1152
return 0
fi
if command -v lspci >/dev/null 2>&1; then
# A non-AMD controller can enumerate first (Intel/ASPEED before an AMD
# dGPU), so scan every display-class line and take the first AMD one
@ -3055,7 +3110,7 @@ if [ "$_torch_index_pinned" = false ] && [ "$SKIP_TORCH" = false ] && \
# whole handoff (a user-set override re-exports unchanged).
export UNSLOTH_ROCM_GFX_ARCH="$_linux_inferred_gfx"
case "$_linux_inferred_gfx" in
gfx1201|gfx1200|gfx1151|gfx1150)
gfx1201|gfx1200|gfx1151|gfx1150|gfx1152)
TORCH_CONSTRAINT="torch>=2.11.0,<2.12.0"
TORCHVISION_CONSTRAINT="torchvision>=0.26.0,<0.27.0"
TORCHAUDIO_CONSTRAINT="torchaudio>=2.11.0,<2.12.0"
@ -3124,7 +3179,7 @@ fi
# and a bare name can resolve a 2.12 ABI-mismatched wheel. Match on the FINAL leaf so a
# custom mirror with a gfx/rocm7.2 path segment but a cu*/cpu family isn't forced.
case "$_torch_index_leaf" in
rocm7.2|gfx120x-all|gfx1151|gfx1150)
rocm7.2|gfx120x-all|gfx1151|gfx1150|gfx1152)
TORCH_CONSTRAINT="torch>=2.11.0,<2.12.0"
TORCHVISION_CONSTRAINT="torchvision>=0.26.0,<0.27.0"
TORCHAUDIO_CONSTRAINT="torchaudio>=2.11.0,<2.12.0"
@ -3243,7 +3298,7 @@ case "$_torch_index_leaf" in
fi
_strix_gfx=""
case "$_runtime_gfx" in
gfx1151|gfx1150) _strix_gfx="$_runtime_gfx" ;;
gfx1151|gfx1150|gfx1152) _strix_gfx="$_runtime_gfx" ;;
esac
# Skip rocm7.13+ generic indexes: they already ship the fixes, so the
# arch build (rocm7.13) would be a downgrade rather than a rescue.
@ -3339,12 +3394,14 @@ elif case "$TORCH_INDEX_URL" in */rocm*|*/gfx*) true ;; *) false ;; esac; then
# gfx1102 matched BEFORE gfx1100 so the spaceless "RX 7700S" lands on
# gfx1102 (bash case has no negative lookahead like the PS tables).
case "$_gpu_disp_mkt" in
*"9070 XT"*|*9080*) _gpu_disp_gfx="gfx1201" ;; # RDNA 4
*9070*|*9060*) _gpu_disp_gfx="gfx1200" ;; # RDNA 4
*9070*|*9080*) _gpu_disp_gfx="gfx1201" ;; # RDNA 4 (Navi 48)
*9060*) _gpu_disp_gfx="gfx1200" ;; # RDNA 4 (Navi 44)
*"8065S"*|*"8060S"*|*"8050S"*|*"8040S"*|*"Strix Halo"*|*"Ryzen AI Max"*|*"AI Max"*) _gpu_disp_gfx="gfx1151" ;; # RDNA 3.5 (Strix Halo + Gorgon Halo: Radeon 8065S/8060S/8050S/8040S iGPU, Ryzen AI Max / Max+)
*"890M"*|*"880M"*|*"860M"*|*"840M"*|*"Strix Point"*|*"Krackan"*|*"HX 37"*|*"AI 9 HX"*|*"AI 9 36"*|*"AI 7 35"*|*"AI 5 34"*|*"AI 7 PRO 35"*|*"AI 5 33"*) _gpu_disp_gfx="gfx1150" ;; # RDNA 3.5 (Strix/Krackan Point: Radeon 890M/880M iGPU, Ryzen AI 9 HX 370/375)
*"RX 7600"*|*"RX 7700S"*|*"RX 7650"*|*"PRO W7600"*|*"PRO W7500"*|*"PRO V710"*) _gpu_disp_gfx="gfx1102" ;; # RDNA 3 (Navi 33)
*"RX 7900"*|*"RX 7800"*|*"RX 7700"*|*"PRO W7900"*|*"PRO W7800"*|*"PRO W7700"*) _gpu_disp_gfx="gfx1100" ;; # RDNA 3 desktop / workstation (Navi 31)
*"890M"*|*"880M"*|*"Strix Point"*|*"HX 37"*|*"AI 9 HX"*|*"AI 9 36"*) _gpu_disp_gfx="gfx1150" ;; # RDNA 3.5 (Strix Point: Radeon 890M/880M, Ryzen AI 9 HX 370/375)
*"860M"*|*"840M"*|*"Krackan"*|*"AI 7 35"*|*"AI 5 34"*|*"AI 7 PRO 35"*|*"AI 5 33"*) _gpu_disp_gfx="gfx1152" ;; # RDNA 3.5 (Krackan Point: Radeon 860M/840M, Ryzen AI 7 350 / AI 5 340)
*"RX 7600"*|*"RX 7700S"*|*"RX 7650"*|*"PRO W7600"*|*"PRO W7500"*) _gpu_disp_gfx="gfx1102" ;; # RDNA 3 (Navi 33)
*"RX 7800"*|*"RX 7700"*|*"PRO W7700"*|*"PRO V710"*) _gpu_disp_gfx="gfx1101" ;; # RDNA 3 (Navi 32)
*"RX 7900"*|*"PRO W7900"*|*"PRO W7800"*) _gpu_disp_gfx="gfx1100" ;; # RDNA 3 desktop / workstation (Navi 31)
*"780M"*|*"760M"*|*"740M"*|*"Phoenix"*|*"Hawk Point"*|*"Z1 Extreme"*|*"Z2 Extreme"*) _gpu_disp_gfx="gfx1103" ;; # RDNA 3 iGPU (Phoenix / Hawk Point)
*"RX 6900"*|*"RX 6800"*|*"RX 6750"*|*"RX 6700"*|*"PRO W6800"*|*"PRO W6900"*) _gpu_disp_gfx="gfx1030" ;; # RDNA 2 (Navi 21)
*"RX 6650"*|*"RX 6600"*|*"PRO W6600"*|*"PRO W6650"*) _gpu_disp_gfx="gfx1032" ;; # RDNA 2 (Navi 23)
@ -4046,9 +4103,11 @@ echo ""
# In non-interactive environments (Docker, CI, cloud-init) just print instructions.
if [ "$_SKIP_AUTOSTART" != true ] && [ -t 1 ]; then
echo ""
printf " Start Unsloth Studio now? [Y/n] "
# No readable answer (closed/EOF tty) defaults to no; Enter is still yes.
if [ -r /dev/tty ]; then
# Prompt only when something can answer: `test -r` passes on the unopenable
# /dev/tty found in containers, leaving a dangling question in the log.
if _can_read_tty; then
printf " Start Unsloth Studio now? [Y/n] "
read -r _reply </dev/tty || _reply="n"
else
_reply="n"

8
scripts/scan_packages_baseline.json
View file

@ -98,6 +98,14 @@
"evidence": "L587: while True: sha256:06c2c7f15d73bf192e5e3272c5ff5fcaeff7f6774fef5f4eca6ef473ae50e2b3",
"evidence_hash": "57acd497f404c203e4450d0580ad85aa8a33406e8d64ad06fbac6cf47d97b24d"
},
{
"package": "fastapi",
"file": "fastapi/routing.py",
"check": "C2 polling/beaconing loop detected",
"severity": "CRITICAL",
"evidence": "L592: while True: sha256:84283c09277ded3296998b2a6a838744457b606829cf5ab5d0da6f222ff020a0",
"evidence_hash": "a7295004315e26a8f3c64fb837521e9fdd7268219bb43e000fb0236ab0259223"
},
{
"package": "fastmcp-slim",
"file": "fastmcp/cli/apps_dev.py",

273
studio/Unsloth_Studio_Colab.ipynb
View file

@ -1,134 +1,145 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/unslothai/unsloth/blob/main/studio/Unsloth_Studio_Colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/unslothai/unsloth/blob/main/studio/Unsloth_Studio_Colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6b87de59"
},
"source": [
"To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n",
"<div class=\"align-center\">\n",
"<a href=\"https://unsloth.ai/\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
"<a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord button.png\" width=\"145\"></a>\n",
"<a href=\"https://unsloth.ai/docs/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a> Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐\n",
"</div>\n",
"\n",
"To install Unsloth Studio on your local device, follow [our guide](https://unsloth.ai/docs/new/unsloth-studio/install). Unsloth Studio is licensed [AGPL-3.0](https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0).\n",
"\n",
"### Unsloth Studio\n",
"\n",
"Train and run open models with [**Unsloth Studio**](https://unsloth.ai/docs/new/unsloth-studio/start). NEW! Installation should now only take 2 mins!\n",
"\n",
"\n",
"We are actively working on making Unsloth Studio install on Colab T4 GPUs faster.\n",
"\n",
"[Features](https://unsloth.ai/docs/new/unsloth-studio#features) • [Quickstart](https://unsloth.ai/docs/new/unsloth-studio/start) • [Data Recipes](https://unsloth.ai/docs/new/unsloth-studio/data-recipe) • [Unsloth Chat](https://unsloth.ai/docs/new/unsloth-studio/chat) • [Export](https://unsloth.ai/docs/new/unsloth-studio/export)"
],
"id": "6b87de59"
},
{
"cell_type": "markdown",
"metadata": {
"id": "e4206349"
},
"source": [
"<p align=\"left\"><img src=\"https://github.com/unslothai/unsloth/raw/main/studio/frontend/public/studio%20github%20landscape%20colab%20display.png\" width=\"600\"></p>"
],
"id": "e4206349"
},
{
"cell_type": "markdown",
"metadata": {
"id": "27da2957"
},
"source": [
"### Setup: Clone repo and run setup"
],
"id": "27da2957"
},
{
"cell_type": "code",
"metadata": {
"id": "27e68f91"
},
"source": "!git clone --depth 1 --branch main https://github.com/unslothai/unsloth.git\n%cd /content/unsloth\n!chmod +x studio/setup.sh && ./studio/setup.sh --local",
"execution_count": null,
"outputs": [],
"id": "27e68f91"
},
{
"cell_type": "markdown",
"metadata": {
"id": "3e1771a9"
},
"source": [
"### Start Unsloth Studio"
],
"id": "3e1771a9"
},
{
"cell_type": "code",
"metadata": {
"id": "277e431e"
},
"source": [
"import sys\n",
"sys.path.insert(0, \"/content/unsloth/studio/backend\")\n",
"from colab import start\n",
"\n",
"# On Colab, start() auto-opens a Cloudflare link and prints admin login credentials.\n",
"# Use the Cloudflare link above the ready card to open Studio (in-cell iframes often stay blank).\n",
"start()\n",
"\n",
"# To skip the Cloudflare tunnel and try the in-notebook proxy iframe only:\n",
"# start(cloudflare=False)"
],
"execution_count": null,
"outputs": [],
"id": "277e431e"
},
{
"cell_type": "markdown",
"metadata": {
"id": "f2b0c6a1"
},
"source": [
"And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n",
"\n",
"Some other resources:\n",
"1. Looking to use Unsloth locally? Read our [Installation Guide](https://unsloth.ai/docs/get-started/install) for details on installing Unsloth on Windows, Docker, AMD, Intel GPUs.\n",
"2. Learn how to do Reinforcement Learning with our [RL Guide and notebooks](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide).\n",
"3. Read our guides and notebooks for [Text-to-speech (TTS)](https://unsloth.ai/docs/basics/text-to-speech-tts-fine-tuning) and [vision](https://unsloth.ai/docs/basics/vision-fine-tuning) model support.\n",
"4. Explore our [LLM Tutorials Directory](https://unsloth.ai/docs/models/tutorials-how-to-fine-tune-and-run-llms) to find dedicated guides for each model.\n",
"5. Need help with Inference? Read our [Inference & Deployment page](https://unsloth.ai/docs/basics/inference-and-deployment) for details on using vLLM, llama.cpp, Ollama etc.\n",
"\n",
"<div class=\"align-center\">\n",
" <a href=\"https://unsloth.ai\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
" <a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord.png\" width=\"145\"></a>\n",
" <a href=\"https://unsloth.ai/docs/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a>\n",
"\n",
" Join Discord if you need help + ⭐️ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐️\n",
"\n",
" <b>This notebook is licensed <a href=\"https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0\">AGPL-3.0</a></b>\n",
"</div>"
],
"id": "f2b0c6a1"
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
{
"cell_type": "markdown",
"id": "6b87de59",
"metadata": {
"id": "6b87de59"
},
"source": [
"To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n",
"<div class=\"align-center\">\n",
"<a href=\"https://unsloth.ai/\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
"<a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord button.png\" width=\"145\"></a>\n",
"<a href=\"https://unsloth.ai/docs/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a> Join Discord if you need help + ⭐ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐\n",
"</div>\n",
"\n",
"To install Unsloth Studio on your local device, follow [our guide](https://unsloth.ai/docs/new/unsloth-studio/install). Unsloth Studio is licensed [AGPL-3.0](https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0).\n",
"\n",
"### Unsloth Studio\n",
"\n",
"Train and run open models with [**Unsloth Studio**](https://unsloth.ai/docs/new/unsloth-studio/start). NEW! Installation should now only take 2 mins!\n",
"\n",
"\n",
"We are actively working on making Unsloth Studio install on Colab T4 GPUs faster.\n",
"\n",
"[Features](https://unsloth.ai/docs/new/unsloth-studio#features) • [Quickstart](https://unsloth.ai/docs/new/unsloth-studio/start) • [Data Recipes](https://unsloth.ai/docs/new/unsloth-studio/data-recipe) • [Unsloth Chat](https://unsloth.ai/docs/new/unsloth-studio/chat) • [Export](https://unsloth.ai/docs/new/unsloth-studio/export)"
]
},
{
"cell_type": "markdown",
"id": "e4206349",
"metadata": {
"id": "e4206349"
},
"source": [
"<p align=\"left\"><img src=\"https://github.com/unslothai/unsloth/raw/main/studio/frontend/public/studio%20github%20landscape%20colab%20display.png\" width=\"600\"></p>"
]
},
{
"cell_type": "markdown",
"id": "27da2957",
"metadata": {
"id": "27da2957"
},
"source": [
"### Setup: Clone repo and run setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "27e68f91",
"metadata": {
"id": "27e68f91"
},
"outputs": [],
"source": "!git clone --depth 1 --branch main https://github.com/unslothai/unsloth.git\n%cd /content/unsloth\n!chmod +x studio/setup.sh && ./studio/setup.sh --local"
},
{
"cell_type": "markdown",
"id": "3e1771a9",
"metadata": {
"id": "3e1771a9"
},
"source": [
"### Start Unsloth Studio"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "277e431e",
"metadata": {
"id": "277e431e"
},
"outputs": [],
"source": "import sys\nsys.path.insert(0, \"/content/unsloth/studio/backend\")\nfrom colab import start\n\n# Default: in-tab iframe only. start() blocks to keep the kernel alive.\nstart()\n\n# For a shareable Cloudflare link, replace start() above with:\n# start(cloudflare=True)"
},
{
"cell_type": "markdown",
"id": "f2b0c6a1",
"metadata": {
"id": "f2b0c6a1"
},
"source": [
"And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n",
"\n",
"Some other resources:\n",
"1. Looking to use Unsloth locally? Read our [Installation Guide](https://unsloth.ai/docs/get-started/install) for details on installing Unsloth on Windows, Docker, AMD, Intel GPUs.\n",
"2. Learn how to do Reinforcement Learning with our [RL Guide and notebooks](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide).\n",
"3. Read our guides and notebooks for [Text-to-speech (TTS)](https://unsloth.ai/docs/basics/text-to-speech-tts-fine-tuning) and [vision](https://unsloth.ai/docs/basics/vision-fine-tuning) model support.\n",
"4. Explore our [LLM Tutorials Directory](https://unsloth.ai/docs/models/tutorials-how-to-fine-tune-and-run-llms) to find dedicated guides for each model.\n",
"5. Need help with Inference? Read our [Inference & Deployment page](https://unsloth.ai/docs/basics/inference-and-deployment) for details on using vLLM, llama.cpp, Ollama etc.\n",
"\n",
"<div class=\"align-center\">\n",
" <a href=\"https://unsloth.ai\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png\" width=\"115\"></a>\n",
" <a href=\"https://discord.gg/unsloth\"><img src=\"https://github.com/unslothai/unsloth/raw/main/images/Discord.png\" width=\"145\"></a>\n",
" <a href=\"https://unsloth.ai/docs/\"><img src=\"https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true\" width=\"125\"></a>\n",
"\n",
" Join Discord if you need help + ⭐️ <i>Star us on <a href=\"https://github.com/unslothai/unsloth\">Github</a> </i> ⭐️\n",
"\n",
" <b>This notebook is licensed <a href=\"https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0\">AGPL-3.0</a></b>\n",
"</div>"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
"nbformat": 4,
"nbformat_minor": 5
}

1
studio/backend/assets/configs/full_finetune.yaml
View file

@ -30,6 +30,7 @@ lora:
vision_all_linear: false
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/lora_text.yaml
View file

@ -30,6 +30,7 @@ lora:
vision_all_linear: false
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/default.yaml
View file

@ -33,6 +33,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/embedding/unsloth_Qwen3-Embedding-0.6B.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/embedding/unsloth_all-MiniLM-L6-v2.yaml
View file

@ -30,6 +30,7 @@ lora:
- "query"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/embedding/unsloth_bge-m3.yaml
View file

@ -30,6 +30,7 @@ lora:
- "value"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/embedding/unsloth_embeddinggemma-300m.yaml
View file

@ -33,6 +33,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/embedding/unsloth_gte-modernbert-base.yaml
View file

@ -29,6 +29,7 @@ lora:
- "Wqkv"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/ernie/unsloth_ERNIE-4.5-21B-A3B-PT.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/ernie/unsloth_ERNIE-4.5-VL-28B-A3B-PT.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/falcon/tiiuae_Falcon-H1-0.5B-Instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_codegemma-7b-bnb-4bit.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_functiongemma-270m-it.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-2-27b-bnb-4bit.yaml
View file

@ -33,6 +33,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-2-2b.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-270m-it.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-27b-it.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-4b-it.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-4b-pt.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3n-E4B-it.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3n-E4B.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-26B-A4B-it.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-26B-A4B.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-31B-it.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-31B.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-E2B-it.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-E2B.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-E4B-it.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-4-E4B.yaml
View file

@ -26,6 +26,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/gpt-oss/unsloth_gpt-oss-120b.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/gpt-oss/unsloth_gpt-oss-20b.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/granite/unsloth_granite-4.0-350m-unsloth-bnb-4bit.yaml
View file

@ -37,6 +37,7 @@ lora:
- "shared_mlp.output_linear"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/granite/unsloth_granite-4.0-h-micro.yaml
View file

@ -37,6 +37,7 @@ lora:
- "shared_mlp.output_linear"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-11B-Vision-Instruct.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-1B-Instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-3B-Instruct.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.3-70B-Instruct.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Meta-Llama-3.1-70B-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_Meta-Llama-3.1-8B-Instruct-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_llama-3-8b-Instruct-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llama/unsloth_llama-3-8b-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/llasa/unsloth_Llasa-3B.yaml
View file

@ -30,6 +30,7 @@ lora:
- "v_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_Magistral-Small-2509-unsloth-bnb-4bit.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_Ministral-3-3B-Instruct-2512.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_Mistral-Nemo-Base-2407-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_Mistral-Small-Instruct-2409.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_Pixtral-12B-2409.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: false

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_mistral-7b-instruct-v0.3-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/mistral/unsloth_mistral-7b-v0.3-bnb-4bit.yaml
View file

@ -33,6 +33,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/OuteAI_Llama-OuteTTS-1.0-1B.yaml
View file

@ -33,6 +33,7 @@ lora:
- "v_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/Spark-TTS-0.5B_LLM.yaml
View file

@ -38,6 +38,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/sesame_csm-1b.yaml
View file

@ -37,6 +37,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_GLM-4.7-Flash.yaml
View file

@ -35,6 +35,7 @@ lora:
- "out_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_LFM2-1.2B.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_Nemotron-3-Nano-30B-A3B.yaml
View file

@ -37,6 +37,7 @@ lora:
- "out_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_PaddleOCR-VL.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/other/unsloth_answerdotai_ModernBERT-large.yaml
View file

@ -33,6 +33,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_orpheus-3b-0.1-ft.yaml
View file

@ -38,6 +38,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_tinyllama-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/other/unsloth_whisper-large-v3.yaml
View file

@ -33,6 +33,7 @@ lora:
- "v_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-3-medium-4k-instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-3.5-mini-instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-4.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/imdatta0_tiny_qwen3_moe_2.8B_0.7B.yaml
View file

@ -36,6 +36,7 @@ lora:
- "gate_up_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2-7B.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2-VL-7B-Instruct.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-1.5B-Instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-7B.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-1.5B-Instruct.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-14B-Instruct.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-7B-Instruct-bnb-4bit.yaml
View file

@ -34,6 +34,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-VL-7B-Instruct-bnb-4bit.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-0.6B.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-14B-Base-unsloth-bnb-4bit.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-14B.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-30B-A3B-Instruct-2507.yaml
View file

@ -36,6 +36,7 @@ lora:
- "gate_up_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-32B.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-4B-Instruct-2507.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-4B-Thinking-2507.yaml
View file

@ -35,6 +35,7 @@ lora:
- "down_proj"
use_rslora: false
use_loftq: false
use_dora: false
logging:
enable_wandb: false

1
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit.yaml
View file

@ -29,6 +29,7 @@ lora:
- "all-linear"
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

1
studio/backend/assets/configs/vision_lora.yaml
View file

@ -30,6 +30,7 @@ lora:
vision_all_linear: true
use_rslora: false
use_loftq: false
use_dora: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true

526
studio/backend/colab.py
View file

@ -1,9 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""
Colab helpers for Unsloth Studio. Uses Colab's built-in proxy.
"""
"""Colab helpers for Unsloth Studio. Uses Colab's built-in proxy."""
from pathlib import Path
import sys
@ -22,11 +20,9 @@ logger = get_logger(__name__)
def get_colab_url(port: int = 8888) -> str:
"""
Get the Colab proxy URL for a port.
"""Get the Colab proxy URL for a port.
Retries up to 3 times, validating the result is a real HTTPS Colab URL.
Falls back to http://localhost:{port} only when all attempts fail.
Retries 3x validating a real HTTPS Colab URL; falls back to localhost on failure.
"""
import time as _time
@ -55,28 +51,243 @@ def get_colab_url(port: int = 8888) -> str:
return fallback
def show_link(port: int = 8888, *, _url: "str | None" = None):
"""Display a styled clickable link to the UI.
*_url* is an optional pre-fetched proxy URL; pass it to avoid a second eval_js round-trip.
"""
from IPython.display import display, HTML
url = _url if _url is not None else get_colab_url(port)
# Truncated display URL; try/except so an odd URL shape still renders the link.
def _short_colab_url(url: str, port: int) -> str:
"""Truncated display form of a Colab proxy URL; falls back to the full URL."""
try:
port_prefix = f"{port}-"
idx = url.index(port_prefix)
next_dash = url.index("-", idx + len(port_prefix))
short_url = url[: next_dash + 1] + "..."
return url[: next_dash + 1] + "..."
except (ValueError, IndexError):
short_url = url
return url
# Plain-text line so the URL shows even if HTML display fails.
logger.info(f"🌐 Unsloth Studio URL: {url}")
html = f"""
def _is_colab_proxy_url(url: str, port: int) -> bool:
"""True when *url* looks like a real Colab kernel proxy, not a localhost fallback."""
return bool(url and isinstance(url, str) and url.startswith("https://") and str(port) in url)
def _is_colab_runtime() -> bool:
"""True on a hosted Colab notebook kernel.
Reuses the backend's main Colab detector (``/content`` + Colab env / ``google.colab``)
instead of a single env var, which is not always present on hosted runtimes.
"""
try:
from main import _IS_COLAB
return bool(_IS_COLAB)
except Exception:
return False
def _colab_login_credentials_path() -> Path:
from auth.storage import DB_PATH
return DB_PATH.parent / ".colab_notebook_login"
def _store_colab_login_credentials(username: str, password: str) -> None:
"""Persist Colab admin credentials for notebook re-runs after interrupt."""
path = _colab_login_credentials_path()
try:
path.parent.mkdir(parents = True, exist_ok = True)
path.write_text(f"{username}\n{password}\n")
try:
import os
os.chmod(path, 0o600)
except OSError:
pass
except OSError as e:
logger.info(f"Could not persist Colab login credentials ({e}).")
def _load_colab_login_credentials() -> "tuple[str, str] | None":
"""Return stored Colab admin credentials from a previous ``start()`` run, if any."""
path = _colab_login_credentials_path()
try:
if not path.is_file():
return None
lines = path.read_text().splitlines()
if len(lines) >= 2 and lines[0] and lines[1]:
return lines[0], lines[1]
except OSError as e:
logger.info(f"Could not load Colab login credentials ({e}).")
return None
def _clear_colab_login_credentials() -> None:
"""Drop the cached Colab credentials once they no longer authenticate."""
path = _colab_login_credentials_path()
try:
path.unlink(missing_ok = True)
except OSError as e:
logger.info(f"Could not clear Colab login credentials ({e}).")
def _colab_credentials_still_valid(username: str, password: str) -> bool:
"""True when *password* still matches the stored admin hash.
Guards against redisplaying a cached first-run password after the user has
changed the admin password through the app, which would print credentials
that no longer authenticate to the current Cloudflare tunnel.
"""
try:
from auth.storage import get_user_and_secret
from auth.hashing import verify_password
except Exception as e:
logger.info(f"Could not load auth to validate cached Colab credentials ({e}).")
return False
try:
row = get_user_and_secret(username)
if not row:
return False
salt, pwd_hash = row[0], row[1]
return bool(verify_password(password, salt, pwd_hash))
except Exception as e:
logger.info(f"Could not validate cached Colab credentials ({e}).")
return False
def _colab_wants_cloudflare(cloudflare: "bool | None") -> bool:
"""Resolve whether to open a Cloudflare tunnel.
``None`` auto-enables on real Colab (the in-cell proxy embed is often blank);
pass ``False`` to opt out.
"""
if cloudflare is not None:
return cloudflare
return _is_colab_runtime()
def _finalize_colab_admin_password() -> "tuple[str, str] | None":
"""Clear the bootstrap-password gate on Colab so Cloudflare tunnels can start.
Returns ``(username, password)`` for display in the notebook. On first run the
random admin password is finalized; on later runs (e.g. after interrupt) the
stored credentials are re-displayed so the Cloudflare link stays usable.
Anyone who can read this cell already controls the runtime.
"""
if not _is_colab_runtime():
return None
try:
from auth.storage import (
DEFAULT_ADMIN_USERNAME,
ensure_default_admin,
generate_bootstrap_password,
get_bootstrap_password,
requires_password_change,
update_password,
)
except Exception as e:
logger.warning(
f"Could not load auth for Colab setup ({e}); Cloudflare link may be blocked."
)
return None
try:
ensure_default_admin()
username = DEFAULT_ADMIN_USERNAME
if not requires_password_change(username):
creds = _load_colab_login_credentials()
if creds is not None and _colab_credentials_still_valid(username, creds[1]):
return creds
# The admin password was changed through the app after the first run,
# so the cached copy is stale; drop it instead of printing dead credentials.
_clear_colab_login_credentials()
return None
password = get_bootstrap_password() or generate_bootstrap_password()
if not update_password(username, password):
logger.warning(
"Could not finalize Colab admin password; Cloudflare link may be blocked."
)
return None
_store_colab_login_credentials(username, password)
return username, password
except Exception as e:
logger.warning(
f"Could not finalize Colab admin password ({e}); Cloudflare link may be blocked."
)
return None
def _colab_login_html(username: str, password: str) -> str:
"""Notebook card with Colab admin credentials (shown once after auto-finalize)."""
return f"""
<div style="display: inline-block; padding: 20px; background: #ffffff; border: 2px solid #000000;
border-radius: 12px; margin: 10px 0; font-family: system-ui, -apple-system, sans-serif;">
<h2 style="color: #000000; margin: 0 0 12px 0; font-size: 22px; font-weight: 800;">
Unsloth Studio Login (Colab)
</h2>
<p style="color: #333333; margin: 0 0 12px 0; font-size: 14px; font-weight: bold;">
Log in as <code>{username}</code> with this password. This cell is visible only in
your notebook session.
</p>
<p style="color: #333333; margin: 0; font-size: 14px; font-family: monospace; font-weight: bold;">
Password: <code>{password}</code>
</p>
</div>
"""
def _show_colab_login_credentials(username: str, password: str) -> None:
"""Display Colab admin credentials in the notebook output."""
from IPython.display import HTML, display
logger.info(f"🔐 Unsloth Studio login — user: {username}")
display(HTML(_colab_login_html(username, password)))
def _ready_card_html(
url: str,
port: int,
*,
has_cloudflare_link: bool = False,
cloudflare_requested: bool = False,
) -> str:
"""Branded ready card for the in-notebook Studio view.
Colab ``*.prod.colab.dev`` proxy URLs are session-scoped and 404 when opened as a
top-level tab or on another device, so never ``window.open`` them. On real Colab the
Cloudflare link is the supported entry point because in-cell proxy embeds often stay blank.
"""
short_url = _short_colab_url(url, port)
if _is_colab_runtime() or _is_colab_proxy_url(url, port):
if has_cloudflare_link:
embed_note = (
"Open Studio with the Cloudflare link above. In-cell proxy previews on "
"current Colab often stay blank, so the tunnel link is the supported path."
)
elif cloudflare_requested:
embed_note = (
"Could not open a Cloudflare tunnel, so Studio may be unreachable on Colab. "
"Check the logs above and re-run this cell. Pass "
'<code style="background:#f3f3f3;padding:2px 6px;border-radius:4px;">'
"cloudflare=True</code> after fixing any tunnel errors."
)
else:
embed_note = (
"Colab proxy links cannot be opened in a new tab (they 404 outside this "
'notebook). Re-run with <code style="background:#f3f3f3;padding:2px 6px;'
'border-radius:4px;">start(cloudflare=True)</code> for a working link.'
)
return f"""
<div style="display: inline-block; padding: 20px; background: #ffffff; border: 2px solid #000000;
border-radius: 12px; margin: 10px 0; font-family: system-ui, -apple-system, sans-serif;">
<h2 style="color: #000000; margin: 0 0 12px 0; font-size: 26px; font-weight: 800;
display: flex; align-items: center; gap: 12px;">
<img src="https://github.com/unslothai/unsloth/raw/main/studio/frontend/public/unsloth-gem.png"
height="48" style="display:block;">
Unsloth Studio is Ready!
</h2>
<p style="color: #333333; margin: 0 0 8px 0; font-size: 15px; font-weight: bold;">
{embed_note}
</p>
<p style="color: #666666; margin: 16px 0 0 0; font-size: 13px; font-family: monospace; font-weight: bold;">
{short_url}
</p>
</div>
"""
return f"""
<div style="display: inline-block; padding: 20px; background: #ffffff; border: 2px solid #000000;
border-radius: 12px; margin: 10px 0; font-family: system-ui, -apple-system, sans-serif;">
<h2 style="color: #000000; margin: 0 0 12px 0; font-size: 26px; font-weight: 800;
@ -100,15 +311,52 @@ def show_link(port: int = 8888, *, _url: "str | None" = None):
</p>
</div>
"""
display(HTML(html))
def show_link(
port: int = 8888,
*,
_url: "str | None" = None,
has_cloudflare_link: bool = False,
cloudflare_requested: bool = False,
):
"""Display a styled ready card for the UI.
Colab proxy URLs are informational only (no new-tab open; they 404 outside the cell);
non-proxy URLs keep a clickable open button. *_url* is an optional pre-fetched proxy
URL to avoid a second eval_js round-trip.
"""
from IPython.display import display, HTML
url = _url if _url is not None else get_colab_url(port)
logger.info(f"🌐 Unsloth Studio URL: {url}")
display(
HTML(
_ready_card_html(
url,
port,
has_cloudflare_link = has_cloudflare_link,
cloudflare_requested = cloudflare_requested,
)
)
)
def _warn_colab_cloudflare_missing(*, use_cloudflare: bool, cloudflare_url: "str | None") -> None:
"""Log a prominent warning when Colab expected a tunnel but none was opened."""
if not use_cloudflare or cloudflare_url or not _is_colab_runtime():
return
logger.warning(
"Colab Cloudflare tunnel unavailable — Studio is unlikely to be reachable in this "
"notebook. Check the logs above for tunnel or auth errors, then re-run start()."
)
def _bootstrap_password_pending() -> bool:
"""True while the default admin still owes a bootstrap-password change.
While pending, main.py injects that password into same-origin GETs, and a public
tunnel GET (no Origin) reads as same-origin, so sharing the link would leak admin
access. Fails safe to pending if the state cannot be read.
While pending, a public tunnel GET (no Origin) reads as same-origin and gets the
injected password, so sharing the link would leak admin access. Fails safe to pending.
"""
try:
from auth.storage import requires_password_change, DEFAULT_ADMIN_USERNAME
@ -121,9 +369,8 @@ def _bootstrap_password_pending() -> bool:
def start_cloudflare_tunnel(port: int) -> "str | None":
"""Open a shareable Cloudflare quick tunnel to localhost:*port*, or None.
run_server suppresses the tunnel on Colab by design, so we start it directly.
Refused while the bootstrap password is pending; any failure collapses to None
and the Colab proxy still works.
run_server suppresses the tunnel on Colab, so we start it directly. Refused while the
bootstrap password is pending; any failure collapses to None (Colab proxy still works).
"""
if _bootstrap_password_pending():
logger.warning(
@ -152,9 +399,9 @@ def start_cloudflare_tunnel(port: int) -> "str | None":
def _publish_cloudflare_url(cloudflare_url: "str | None") -> None:
"""Publish a directly-started tunnel URL onto app.state so /api/health advertises it.
run_server only sets this when it opens the tunnel itself, which it skips on Colab,
so we set it here. Otherwise the frontend's API examples fall back to an
unreachable server_url. Best-effort.
run_server sets this only when it opens the tunnel itself (skipped on Colab), so we
set it here; otherwise the frontend's API examples fall back to an unreachable
server_url. Best-effort.
"""
if not cloudflare_url:
return
@ -183,8 +430,7 @@ def _stop_cloudflare_tunnel() -> None:
def _is_studio_healthy(port: int, timeout: float = 2.0) -> bool:
"""True only if Unsloth Studio (not some other app) answers /api/health on *port*.
The service-marker check stops the reuse path reusing or tunneling a foreign
process that merely serves /api/health.
The service-marker check stops the reuse path reusing or tunneling a foreign process.
"""
import json, urllib.request
try:
@ -194,8 +440,29 @@ def _is_studio_healthy(port: int, timeout: float = 2.0) -> bool:
return False
def _shareable_link_html(cloudflare_url: str) -> str:
"""Branded card for the shareable Cloudflare link, styled like the show_link banner."""
def _shareable_link_html(
cloudflare_url: str,
password: "str | None" = None,
username: "str | None" = None,
) -> str:
"""Branded card for the shareable Cloudflare link, styled like the show_link banner.
*password* renders under the link so the credential sits in the card with the button
it unlocks. The username is always the default admin, so it reads inline.
"""
login_block = ""
if password:
login_block = f"""
<p style="color: #000000; margin: 16px 0 0 0; font-size: 20px; font-weight: 800;">
Password
</p>
<p style="margin: 6px 0 0 0;"><code style="display: inline-block; font-size: 24px;
font-weight: 800; text-decoration: underline; background: #f3f3f3;
padding: 4px 10px; border-radius: 6px;">{password}</code></p>
<p style="color: #666666; margin: 6px 0 0 0; font-size: 12px;">
Log in as <code>{username}</code> with this password. Shown only in your
notebook session, and never included in the shared link.
</p>"""
return f"""
<div style="display: inline-block; padding: 20px; background: #ffffff; border: 2px solid #000000;
border-radius: 12px; margin: 10px 0; font-family: system-ui, -apple-system, sans-serif;">
@ -213,40 +480,55 @@ def _shareable_link_html(cloudflare_url: str) -> str:
Open Unsloth Studio
</a>
<p style="color: #333333; margin: 12px 0 0 0; font-size: 14px; font-weight: bold;">
This Cloudflare HTTPS link works from any device — share it with anyone. The Colab view below only works in this tab.
This Cloudflare HTTPS link works from any device, so you can share it with anyone.
</p>
<p style="color: #333333; margin: 16px 0 0 0; font-size: 13px; font-family: monospace; font-weight: bold;">
🔗 {cloudflare_url}
</p>
🔗 <a href="{cloudflare_url}" onclick="var w=window.open(this.href,'_blank');if(!w){{return true;}}return false;"
style="color: #000000; text-decoration: underline; cursor: pointer;">{cloudflare_url}</a>
</p>{login_block}
</div>
"""
def _show_and_embed(port: int, *, cloudflare_url: "str | None" = None):
"""Render the Unsloth header + iframe for *port*, with a shareable-link card above
when *cloudflare_url* is set. Falls back to serve_kernel_port_as_iframe."""
url = get_colab_url(port)
logger.info(f"🌐 Unsloth Studio URL: {url}")
if cloudflare_url:
logger.info(f"🔗 Shareable Cloudflare link: {cloudflare_url}")
# Height for serve_kernel_port_as_iframe (~82vh on a 1080p screen, clamped).
_COLAB_IFRAME_HEIGHT = 900
def _embed_kernel_port_iframe(port: int) -> bool:
"""Embed Studio via Colab's native kernel-port iframe helper.
Only trusted on a real Colab runtime: colabtools can import ``google.colab`` and
queue browser-side JS without appending an iframe, so callers outside Colab must use
the HTML iframe path instead.
"""
if not _is_colab_runtime():
return False
try:
from google.colab import output as colab_output
except ImportError:
return False
try:
colab_output.serve_kernel_port_as_iframe(
port,
height = _COLAB_IFRAME_HEIGHT,
width = "100%",
)
return True
except Exception as e:
logger.info(f"serve_kernel_port_as_iframe failed ({e}); trying HTML iframe.")
return False
def _embed_html_iframe(url: str, port: int) -> bool:
"""Fallback embed: raw HTML iframe when the Colab helper is unavailable."""
try:
from IPython.display import HTML, display
except ImportError:
return False
iframe_id = f"unsloth-studio-{port}"
# Truncated header URL — best-effort, falls back to full URL.
try:
port_prefix = f"{port}-"
idx = url.index(port_prefix)
next_dash = url.index("-", idx + len(port_prefix))
short_url = url[: next_dash + 1] + "..."
except (ValueError, IndexError):
short_url = url
if cloudflare_url:
display(HTML(_shareable_link_html(cloudflare_url)))
short_url = _short_colab_url(url, port)
iframe_id = f"unsloth-studio-{port}"
try:
display(
HTML(f"""
<div style="font-family:system-ui,-apple-system,sans-serif;margin:8px 0;
@ -266,41 +548,110 @@ def _show_and_embed(port: int, *, cloudflare_url: "str | None" = None):
</div>
""")
)
except Exception:
# Fallback: Colab's built-in helper.
return True
except Exception as e:
logger.info(f"HTML iframe embed failed ({e}).")
return False
def _show_and_embed(
port: int,
*,
cloudflare_url: "str | None" = None,
colab_login: "tuple[str, str] | None" = None,
cloudflare_requested: bool = False,
):
"""Render the Unsloth ready card + iframe for *port*.
Prefer Colab's ``serve_kernel_port_as_iframe`` on real Colab; raw HTML iframe is the
fallback. Cloudflare cards stay clickable.
"""
url = get_colab_url(port)
logger.info(f"🌐 Unsloth Studio URL: {url}")
if cloudflare_url:
logger.info(f"🔗 Shareable Cloudflare link: {cloudflare_url}")
_warn_colab_cloudflare_missing(
use_cloudflare = cloudflare_requested,
cloudflare_url = cloudflare_url,
)
# Fold the credentials into the link card rather than a second card below it.
credentials_shown = False
if cloudflare_url:
try:
from google.colab import output as colab_output
colab_output.serve_kernel_port_as_iframe(port, height = 900, width = "100%")
except ImportError:
pass
from IPython.display import HTML, display
username, password = colab_login if colab_login else (None, None)
display(HTML(_shareable_link_html(cloudflare_url, password, username)))
credentials_shown = bool(colab_login)
except Exception as e:
logger.info(f"Could not render Cloudflare link card ({e}).")
if colab_login and not credentials_shown:
try:
_show_colab_login_credentials(*colab_login)
except Exception as e:
logger.info(f"Could not render Colab login card ({e}).")
# With a tunnel up the embed below is skipped, so the ready card would only restate
# the link card and print a proxy URL that 404s outside this tab.
skip_ready_card = _is_colab_runtime() and bool(cloudflare_url)
if not skip_ready_card:
try:
show_link(
port,
_url = url,
has_cloudflare_link = bool(cloudflare_url),
cloudflare_requested = cloudflare_requested,
)
except Exception as e:
logger.info(f"Could not render Unsloth link card ({e}).")
# On Colab with a working tunnel, skip the in-cell proxy embed (often blank).
if _is_colab_runtime() and cloudflare_url:
return
# Real Colab: kernel helper needs only the port (works when eval_js failed).
if _is_colab_runtime():
if _embed_kernel_port_iframe(port):
return
_embed_html_iframe(url, port)
def start(port: int = 8888, *, cloudflare: bool = False):
def start(port: int = 8888, *, cloudflare: "bool | None" = None):
"""Start Unsloth Studio in Colab and display the URL.
Args:
port: Port to bind/serve on.
cloudflare: Opt in to a shareable Cloudflare HTTPS link reachable from any
device (default OFF). It exposes Unsloth's login page beyond Colab, so it
stays an explicit opt-in; the default shows only the in-tab proxy iframe.
cloudflare: Shareable Cloudflare HTTPS link. ``None`` (default) auto-enables on
real Colab because the in-cell proxy embed is often blank; pass ``False`` to
skip the tunnel or ``True`` to force it on other runtimes.
Usage:
start() # Colab-proxy iframe only (default)
start(cloudflare=True) # also open a shareable Cloudflare link
start() # Cloudflare link on Colab (auto); proxy iframe elsewhere
start(cloudflare=False) # Colab proxy iframe only (often blank on current Colab)
start(cloudflare=True) # force Cloudflare link on any runtime
"""
import time
logger.info("🦥 Starting Unsloth Studio...")
use_cloudflare = _colab_wants_cloudflare(cloudflare)
# Fast path: Unsloth already running (cell re-run). Re-launching would collide on
# the port, so just re-show the link and iframe.
# Fast path: already running (cell re-run); re-show link/iframe instead of rebinding the port.
if _is_studio_healthy(port):
logger.info(f" Unsloth is already running on port {port} — reusing existing server.")
# try/finally: tear the tunnel down even if interrupted mid-start/render.
try:
cf_url = start_cloudflare_tunnel(port) if cloudflare else None
colab_login = _finalize_colab_admin_password() if use_cloudflare else None
cf_url = start_cloudflare_tunnel(port) if use_cloudflare else None
_publish_cloudflare_url(cf_url)
_show_and_embed(port, cloudflare_url = cf_url)
_show_and_embed(
port,
cloudflare_url = cf_url,
colab_login = colab_login,
cloudflare_requested = use_cloudflare,
)
for _ in range(10000):
time.sleep(300)
print("=", end = "", flush = True)
@ -313,7 +664,6 @@ def start(port: int = 8888, *, cloudflare: bool = False):
logger.info(" Loading backend...")
from run import run_server
# Auto-detect frontend path
repo_root = Path(__file__).parent.parent
frontend_path = repo_root / "frontend" / "dist"
@ -323,8 +673,7 @@ def start(port: int = 8888, *, cloudflare: bool = False):
logger.info(" Starting server...")
try:
# cloudflare=False: this helper owns the tunnel (Colab's own
# start(cloudflare=...) drives it), so pin it off explicitly.
# cloudflare=False: this helper owns the tunnel (via start(cloudflare=...)), so pin it off.
app = run_server(
host = "0.0.0.0",
port = port,
@ -339,14 +688,12 @@ def start(port: int = 8888, *, cloudflare: bool = False):
logger.error(f"❌ Unsloth Studio failed to start: {exc}")
return
# run_server auto-increments the port if in use; read back the bound port so the
# proxy URL and iframe point at the right place.
# run_server may auto-increment the port; read back the bound port for the proxy URL/iframe.
actual_port: int = getattr(getattr(app, "state", None), "server_port", None) or port
logger.info(f" Server started on port {actual_port}!")
# Poll health endpoint before showing the link — avoids the race where ready_event
# fires but the process hasn't finished binding.
# Poll health before showing the link: avoids the race where ready_event fires pre-bind.
import urllib.request
server_ready = False
@ -365,12 +712,17 @@ def start(port: int = 8888, *, cloudflare: bool = False):
)
return
# Open the tunnel now the server is healthy, publish its URL for /api/health, and
# tear it down on interrupt (try/finally) rather than orphan the process.
# Server healthy: finalize Colab auth, open the tunnel, publish URL, tear down on interrupt.
try:
cf_url = start_cloudflare_tunnel(actual_port) if cloudflare else None
colab_login = _finalize_colab_admin_password() if use_cloudflare else None
cf_url = start_cloudflare_tunnel(actual_port) if use_cloudflare else None
_publish_cloudflare_url(cf_url)
_show_and_embed(actual_port, cloudflare_url = cf_url)
_show_and_embed(
actual_port,
cloudflare_url = cf_url,
colab_login = colab_login,
cloudflare_requested = use_cloudflare,
)
# Keep kernel alive so the daemon server thread runs.
for _ in range(10000):

152
studio/backend/core/export/export.py
View file

@ -81,6 +81,82 @@ _PYTORCH_MISSING_MESSAGE = (
_LLAMA_CPP_SCRIPTS_WARNING_EMITTED = False
def _multi_gpu_device_map_kwargs() -> dict:
"""``device_map`` kwargs for sharding a checkpoint across every visible GPU.
unsloth's ``from_pretrained`` defaults to ``device_map="sequential"``, which stacks
the whole model on GPU0 and OOMs multi-GPU hosts whose other GPUs sit empty (#7053).
Returns ``{"device_map": "balanced"}`` only on a real multi-GPU CUDA/ROCm host
(mirroring the inference loader's ``get_device_map``), else empty so single-GPU, CPU
and MLX loads keep the loader default."""
if _IS_MLX:
return {}
try:
from utils.hardware import get_device_map, get_parent_visible_gpu_ids
visible = get_parent_visible_gpu_ids()
if len(visible) > 1:
device_map = get_device_map(visible)
elif not visible:
# UUID/MIG masks resolve to no numeric ids; get_device_map(None) falls back
# to the visible-GPU count, so a multi-GPU UUID/MIG host still shards.
device_map = get_device_map(None)
else:
return {}
if device_map == "balanced":
return {"device_map": device_map}
except Exception as exc:
logger.debug(f"multi-GPU device_map resolution failed; using loader default: {exc}")
return {}
def _is_oom_error(exc: BaseException) -> bool:
"""True for an accelerator OOM, however it is spelled.
accelerate and transformers re-raise it as a plain ``RuntimeError`` on several paths
and ROCm/XPU use their own classes, so match the message too.
"""
if torch is not None:
oom_types = tuple(
t
for t in (
getattr(torch, "OutOfMemoryError", None),
getattr(getattr(torch, "cuda", None), "OutOfMemoryError", None),
getattr(getattr(torch, "xpu", None), "OutOfMemoryError", None),
)
if isinstance(t, type)
)
if oom_types and isinstance(exc, oom_types):
return True
return "out of memory" in f"{type(exc).__name__}: {exc}".lower()
def _is_cpu_spill_rejection(exc: BaseException) -> bool:
"""bitsandbytes refuses a map that spills to CPU/disk with a plain ``ValueError``.
Busy secondary GPUs can make ``balanced`` spill to CPU even where the old sequential
load fit on GPU0, and that message says nothing about memory, so the retry has to
match it explicitly. See transformers ``quantizers/quantizer_bnb_4bit.py``.
"""
return "dispatched on the cpu or the disk" in str(exc).lower()
class _CpuSpillRetry(Exception):
"""A multi-GPU load that succeeded but left modules offloaded to CPU/disk."""
def _cpu_offloaded_modules(model) -> int:
"""Count the modules a load parked on CPU or disk.
Only bitsandbytes refuses such a map; a full-precision load accepts it, leaves the
parameters on meta and dies much later in safetensors with "Cannot copy out of meta
tensor". Nothing raises at load time, so inspect the map directly. PEFT re-dispatches
when attaching an adapter, so in practice this catches merged checkpoints.
"""
device_map = getattr(model, "hf_device_map", None) or {}
return sum(1 for target in device_map.values() if str(target) in ("cpu", "disk"))
def _supports_kwarg(fn, name):
"""True if `fn` accepts keyword `name` directly or via **kwargs."""
import inspect
@ -271,6 +347,7 @@ class ExportBackend:
load_in_4bit: bool = True,
trust_remote_code: bool = False,
hf_token: Optional[str] = None,
_device_map_override: Optional[dict] = None,
) -> Tuple[bool, str]:
"""
Load a checkpoint for export.
@ -303,6 +380,14 @@ class ExportBackend:
# Skip the Hub when offline so a no-internet export uses the local cache.
local_files_only = _hf_offline()
# Shard across every visible GPU instead of stacking on GPU0 (#7053); {} on
# single-GPU/CPU/MLX. _device_map_override is the single-device retry below.
_device_map_kw = (
_multi_gpu_device_map_kwargs()
if _device_map_override is None
else _device_map_override
)
# Run the type-detection probes in the forced-offline window (else a gated
# base 404s); it covers is_vision_model's Hub reads + the transformers-5
# subprocess, and local_files_only makes detect_audio_type's requests.get skip.
@ -328,6 +413,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
elif self._audio_type == "whisper":
@ -343,6 +429,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
elif self._audio_type == "snac":
@ -355,6 +442,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
elif self._audio_type == "bicodec":
@ -368,6 +456,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
elif self._audio_type == "dac":
@ -380,6 +469,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
elif self.is_vision:
@ -392,6 +482,7 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
tokenizer = processor # vision: processor acts as tokenizer
@ -405,8 +496,16 @@ class ExportBackend:
trust_remote_code = trust_remote_code,
token = token,
local_files_only = local_files_only,
**_device_map_kw,
)
# Only when we asked for the multi-GPU map: a single-GPU host has no second
# placement to retry on, so leave its behaviour untouched.
_offloaded = _cpu_offloaded_modules(model) if _device_map_kw else 0
if _device_map_override is None and _offloaded:
del model
raise _CpuSpillRetry(f"{_offloaded} module(s) offloaded to CPU/disk")
if _IS_MLX:
# MLX doesn't use PeftModel — detect LoRA via adapter_config.json
self.is_peft = adapter_config.exists()
@ -429,11 +528,41 @@ class ExportBackend:
return True, f"Loaded {model_type} model{peft_info} successfully"
except Exception as e:
logger.error(f"Error loading checkpoint: {e}")
import traceback
# Sharding is an optimisation, never a requirement. "balanced" budgets from the
# free memory read BEFORE this process opens a CUDA context on each GPU, so when
# a training or chat job already owns the others the shard can OOM, or spill to
# CPU and be refused by bitsandbytes, where the old single-device load succeeded.
# Fall back once before giving up.
if (
_device_map_override is None
and (
isinstance(e, _CpuSpillRetry) or _is_oom_error(e) or _is_cpu_spill_rejection(e)
)
and _multi_gpu_device_map_kwargs()
):
# Retry outside this block: the live traceback pins the half-built model's
# frames, so an in-block retry inherits the exhausted device.
retry_reason = str(e)
else:
logger.error(f"Error loading checkpoint: {e}")
import traceback
logger.error(traceback.format_exc())
return False, f"Failed to load checkpoint: {str(e)}"
logger.error(traceback.format_exc())
return False, f"Failed to load checkpoint: {str(e)}"
logger.warning(
f"Multi-GPU export load unusable ({retry_reason}); retrying on "
f"the single-device loader default."
)
self.cleanup_memory()
return self.load_checkpoint(
checkpoint_path,
max_seq_length = max_seq_length,
load_in_4bit = load_in_4bit,
trust_remote_code = trust_remote_code,
hf_token = hf_token,
_device_map_override = {},
)
def _write_export_metadata(self, save_directory: str):
"""Write export_metadata.json with base model info for Chat page discovery."""
@ -1048,6 +1177,21 @@ class ExportBackend:
"Use the safetensors adapter instead.",
None,
)
# llama.cpp's convert_lora_to_gguf.py has no concept of DoRA's
# lora_magnitude_vector tensors: it only reads the standard
# lora_A/lora_B delta, so exporting a DoRA adapter would silently
# drop the magnitude rescaling and produce a GGUF LoRA file that
# loads fine but no longer matches the trained model.
_peft_config = getattr(self.current_model, "peft_config", {}).get("default")
if getattr(_peft_config, "use_dora", False):
return (
False,
"GGUF LoRA export is not supported for DoRA adapters: the GGUF LoRA "
"format has no way to represent DoRA's magnitude vectors, so the "
"exported file would silently lose the DoRA behavior. Use the "
"safetensors adapter instead, or merge to a full GGUF model.",
None,
)
outtype = str(gguf_outtype).lower()
if outtype not in _GGUF_LORA_OUTTYPES:
return (

25
studio/backend/core/inference/inference.py
View file

@ -8,6 +8,7 @@ from unsloth.chat_templates import get_chat_template
from transformers import TextIteratorStreamer, TextStreamer
from peft import PeftModel, PeftModelForCausalLM
import contextlib
import json
import sys
import torch
@ -1942,8 +1943,30 @@ class InferenceBackend:
+ text
+ "<|text_end|>\n<|audio_start|><|global_features_start|>\n"
)
with torch.inference_mode():
with torch.amp.autocast("cuda", dtype = model.dtype):
# Derive the autocast device from the loaded model, not from the
# global backend: a CPU-fallback DAC on an XPU/CUDA host must not
# open a GPU autocast context around CPU tensors.
device_type = (
model.device.type
if hasattr(model.device, "type")
else str(model.device).split(":", 1)[0]
)
# Clamp to autocast-supported backends so exotic devices
# (e.g. "meta" during accelerate offloaded loading) do not raise.
# MPS is autocast-supported since torch 2.3, keep it in the set.
if device_type not in ("cuda", "xpu", "mps", "cpu"):
device_type = "cpu"
# CPU and XPU autocast only accept bfloat16/float16. For a
# float32 model, skip autocast entirely to avoid raising or
# producing a warning on every generate call.
autocast_dtype_supported = model.dtype in (torch.bfloat16, torch.float16)
if device_type in ("cpu", "xpu") and not autocast_dtype_supported:
autocast_ctx = contextlib.nullcontext()
else:
autocast_ctx = torch.amp.autocast(device_type, dtype = model.dtype)
with autocast_ctx:
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
generated = model.generate(
**inputs,

749
studio/backend/core/inference/llama_cpp.py
View file

File diff suppressed because it is too large Load diff

65
studio/backend/core/inference/local_model_resolver.py
View file

@ -147,10 +147,16 @@ def _build_index() -> dict[str, _LocalGgufEntry]:
)
from utils.paths import legacy_hf_cache_dir, hf_default_cache_dir, lmstudio_model_dirs
from utils.hf_cache_settings import known_hf_hub_caches
from core.inference.model_ids import public_model_id
index: dict[str, _LocalGgufEntry] = {}
seen_hf: set[str] = set()
try:
active_root = str(Path(_resolve_hf_cache_dir()).resolve())
except Exception:
active_root = None
def _scan_hf_once(directory) -> list:
if directory is None:
return []
@ -162,7 +168,13 @@ def _build_index() -> dict[str, _LocalGgufEntry]:
if rp in seen_hf:
return []
seen_hf.add(rp)
return _scan_hf_cache(directory)
# Only the active cache loads by repo id. Say so, or an inactive repo is
# indexed under an id it cannot load by, and its snapshot basename (what
# /v1/models advertises once loaded by path) is never a key at all.
# No format classification here: nothing on this path reads model_format,
# and its recursive walk would duplicate the one _local_gguf_entry already
# does per snapshot, on the request path.
return _scan_hf_cache(directory, active_cache = rp == active_root, classify_format = False)
except Exception as exc: # a missing/malformed root must skip, never crash the index
logger.debug("auto-switch: skipping HF cache dir %r: %s", directory, exc)
return []
@ -220,12 +232,61 @@ def _build_index() -> dict[str, _LocalGgufEntry]:
continue
# Index every alias (including the path) so a client can resolve by any of
# them, even though only the non-path loader_id is advertised.
for key in (raw_id, getattr(info, "model_id", None), getattr(info, "display_name", None)):
for key in (
raw_id,
getattr(info, "model_id", None),
getattr(info, "display_name", None),
public_model_id(raw_id),
):
if key:
index.setdefault(key.strip().lower(), entry)
# Other revisions of the same repo resolve to their own weights, so a pin on
# one keeps working after Hugging Face writes a newer snapshot.
for name, sibling_entry in _sibling_revision_entries(raw_id, loader_id):
index.setdefault(name.strip().lower(), sibling_entry)
return index
def _sibling_revision_entries(raw_id: str, loader_id: str):
"""Yield ``(revision_name, entry)`` for the repo's OTHER cached revisions.
An inactive-cache repo carries its snapshot path as the id, and /v1/models
advertises only that directory's basename once loaded, so anything durable
pinned to it (a subagent config) holds one revision hash. Hugging Face writes a
new snapshot dir on every update, and the scan emits a single entry per repo
pointed at the newest one, so that pin would otherwise stop resolving and drop
through to whatever model is loaded.
Each revision gets an entry for its OWN directory rather than an alias onto the
scanned one: aliasing would redirect a pin that names an older complete revision
onto a newer half-downloaded snapshot and break a request that works today.
Incomplete revisions are skipped for the same reason.
Sibling names are only revisions inside a real cache repo
(``<root>/models--org--name/snapshots/<rev>``). A scan folder that merely happens
to be called ``snapshots`` holds unrelated models, and treating those as
revisions would silently serve one model in place of another.
"""
from pathlib import Path
from types import SimpleNamespace
snapshots = Path(raw_id).parent
if snapshots.name != "snapshots" or not snapshots.parent.name.startswith("models--"):
return
from routes.models import snapshot_variants_all_complete
try:
siblings = [p for p in snapshots.iterdir() if p.is_dir() and p.name != Path(raw_id).name]
except OSError:
return
for sibling in siblings:
if not snapshot_variants_all_complete(str(sibling)):
continue
entry = _local_gguf_entry(loader_id, SimpleNamespace(path = str(sibling)))
if entry is not None:
yield sibling.name, entry
def _index() -> dict[str, _LocalGgufEntry]:
global _scan
# Build under the lock so concurrent callers with an expired cache don't all

4
studio/backend/core/inference/orchestrator.py
View file

@ -27,7 +27,7 @@ import uuid
from io import BytesIO
from pathlib import Path
from typing import Any, Generator, Optional, Tuple, Union
from utils.hardware import prepare_gpu_selection
from utils.hardware import get_device, prepare_gpu_selection
# Re-exported from the shared helper so GGUF, training, and inference share one
# type; kept importable here for backwards compatibility.
@ -1012,6 +1012,8 @@ class InferenceOrchestrator:
)
sub_config["resolved_gpu_ids"] = resolved_gpu_ids
sub_config["gpu_selection"] = gpu_selection
# Parent-detected backend for the worker's apply_gpu_ids().
sub_config["device_backend"] = get_device().value
# Recheck the sidecar reservation BEFORE tearing the old worker down,
# for REPAIRS only: an install holds this same lifecycle gate, so it

23
studio/backend/core/inference/safetensors_agentic.py
View file

@ -514,13 +514,17 @@ def run_safetensors_tool_loop(
"""
conversation = list(messages)
# Normalize the mode (mirrors the GGUF loop): "full" and
# bypass_permissions are the same switch; unset/unknown behaves as "ask".
# "off" keeps the sandbox but never prompts.
# Mirrors the GGUF loop: "full" and bypass_permissions are the same switch;
# unset defaults to "auto", unknown falls back to the stricter "ask"; "off"
# keeps the sandbox but never prompts. An explicit confirm_tool_calls=True with
# no mode is already resolved to "ask" at the request layer, so it never
# arrives here as an ambiguous unset.
if permission_mode == "full":
bypass_permissions = True
elif bypass_permissions:
permission_mode = "full"
elif permission_mode is None:
permission_mode = "auto"
elif permission_mode not in ("ask", "auto", "off"):
permission_mode = "ask"
@ -1189,18 +1193,15 @@ def run_safetensors_tool_loop(
else:
assistant_msg.setdefault("tool_calls", []).append(decision.as_assistant_tool_call())
# Bypass wins over the confirm gate at the loop level too, so a
# direct internal caller passing both flags never prompts. In
# "auto" mode only calls detected as potentially unsafe pause.
# "off" never prompts (sandbox stays on).
# Bypass wins here too, so a direct internal caller with both flags
# never prompts. "auto" pauses only high-risk calls; "off" never
# prompts (sandbox stays on).
needs_confirm = (
bool(confirm_tool_calls) and not bypass_permissions and permission_mode != "off"
)
if needs_confirm and permission_mode == "auto":
from core.inference.tools import is_potentially_unsafe_tool_call
needs_confirm = is_potentially_unsafe_tool_call(
decision.tool_name, decision.arguments
)
from core.inference.tools import is_high_risk_tool_call
needs_confirm = is_high_risk_tool_call(decision.tool_name, decision.arguments)
approval_id = new_approval_id() if needs_confirm else ""
decision_slot = begin_tool_decision(session_id, approval_id) if needs_confirm else None
start_event = decision.tool_start_event()

2431
studio/backend/core/inference/tools.py
View file

File diff suppressed because it is too large Load diff

2
studio/backend/core/inference/worker.py
View file

@ -794,7 +794,7 @@ def run_inference_process(
env = os.getenv("ENVIRONMENT_TYPE", "production"),
)
apply_gpu_ids(config.get("resolved_gpu_ids"))
apply_gpu_ids(config.get("resolved_gpu_ids"), backend = config.get("device_backend"))
model_name = config["model_name"]

22
studio/backend/core/training/trainer.py
View file

@ -891,6 +891,7 @@ class UnslothTrainer:
use_gradient_checkpointing: str = "unsloth",
use_rslora: bool = False,
use_loftq: bool = False,
use_dora: bool = False,
modules_to_save: list = None,
) -> bool:
"""
@ -993,6 +994,7 @@ class UnslothTrainer:
use_gradient_checkpointing = use_gradient_checkpointing,
random_state = 3407,
use_rslora = use_rslora,
use_dora = use_dora,
loftq_config = {"loftq_bits": 4, "loftq_iter": 1} if use_loftq else None,
)
# Audio VLM models support VLM-style layer selection
@ -1023,6 +1025,7 @@ class UnslothTrainer:
use_gradient_checkpointing = use_gradient_checkpointing,
random_state = 3407,
use_rslora = use_rslora,
use_dora = use_dora,
loftq_config = {"loftq_bits": 4, "loftq_iter": 1} if use_loftq else None,
task_type = None,
)
@ -1042,6 +1045,7 @@ class UnslothTrainer:
use_gradient_checkpointing = use_gradient_checkpointing,
random_state = 3407,
use_rslora = use_rslora,
use_dora = use_dora,
loftq_config = {"loftq_bits": 4, "loftq_iter": 1} if use_loftq else None,
)
@ -1067,6 +1071,7 @@ class UnslothTrainer:
use_gradient_checkpointing = use_gradient_checkpointing,
random_state = 3407,
use_rslora = use_rslora,
use_dora = use_dora,
loftq_config = {"loftq_bits": 4, "loftq_iter": 1} if use_loftq else None,
modules_to_save = modules_to_save,
)
@ -1087,6 +1092,7 @@ class UnslothTrainer:
use_gradient_checkpointing = use_gradient_checkpointing,
random_state = 3407,
use_rslora = use_rslora,
use_dora = use_dora,
loftq_config = {"loftq_bits": 4, "loftq_iter": 1} if use_loftq else None,
modules_to_save = modules_to_save,
)
@ -1481,6 +1487,9 @@ class UnslothTrainer:
SNAC_MODEL_NAME = "hubertsiuzdak/snac_24khz"
SNAC_SAMPLE_RATE = 24000
# SNAC codec unvalidated on Intel XPU; keep the pre-PR CPU
# fallback for non-CUDA hosts.
device = "cuda" if torch.cuda.is_available() else "cpu"
max_length = self.max_seq_length or 2048
tokenizer = self.tokenizer
@ -1642,7 +1651,8 @@ class UnslothTrainer:
del snac_model
gc.collect()
torch.cuda.empty_cache()
clear_gpu_cache()
self._cuda_audio_used = True
if not processed_examples:
@ -1669,6 +1679,8 @@ class UnslothTrainer:
import numpy as np
import torchaudio.transforms as T
# Spark-TTS BiCodec unvalidated on Intel XPU; keep the pre-PR CPU
# fallback for non-CUDA hosts.
device = "cuda" if torch.cuda.is_available() else "cpu"
# sparktts lives in the SparkAudio/Spark-TTS GitHub repo, not the HF model
@ -1857,7 +1869,8 @@ class UnslothTrainer:
del audio_tokenizer
gc.collect()
torch.cuda.empty_cache()
clear_gpu_cache()
self._cuda_audio_used = True
if not processed_examples:
@ -1894,6 +1907,8 @@ class UnslothTrainer:
from datasets import Dataset as HFDataset
from utils.paths import ensure_dir, tmp_root
# OuteTTS DAC/Whisper preprocess unvalidated on Intel XPU; keep the
# pre-PR CPU fallback for non-CUDA hosts.
device = "cuda" if torch.cuda.is_available() else "cpu"
# Clone OuteTTS repo (same as audio_codecs._load_dac)
@ -2065,7 +2080,8 @@ class UnslothTrainer:
del prompt_processor
gc.collect()
torch.cuda.empty_cache()
clear_gpu_cache()
self._cuda_audio_used = True
if not processed_examples:

9
studio/backend/core/training/training.py
View file

@ -30,7 +30,7 @@ from typing import Optional, Tuple, Any, Callable, Union, TYPE_CHECKING
if TYPE_CHECKING:
import matplotlib.pyplot as plt
from utils.hardware import prepare_gpu_selection
from utils.hardware import get_device, prepare_gpu_selection
from utils.native_path_leases import (
native_path_secret_removed_for_child_start,
run_without_native_path_secret,
@ -196,6 +196,7 @@ def _build_training_worker_config(values: dict[str, Any]) -> dict[str, Any]:
"gradient_checkpointing": values.get("gradient_checkpointing", "unsloth"),
"use_rslora": values.get("use_rslora", False),
"use_loftq": values.get("use_loftq", False),
"use_dora": values.get("use_dora", False),
"train_on_completions": values.get("train_on_completions", False),
"finetune_vision_layers": values.get("finetune_vision_layers", True),
"finetune_language_layers": values.get("finetune_language_layers", True),
@ -219,6 +220,9 @@ def _build_training_worker_config(values: dict[str, Any]) -> dict[str, Any]:
config[key] = values.get(key)
if config["training_type"] == "Full Finetuning":
config["load_in_4bit"] = False
# The parent's detected backend: the worker's apply_gpu_ids() targets the
# right visibility env var from this, without probing torch pre-mask.
config["device_backend"] = get_device().value
return config
@ -452,6 +456,7 @@ class _MLXTrainerAdapter:
use_gradient_checkpointing: Union[str, bool] = "unsloth",
use_rslora: bool = False,
use_loftq: bool = False,
use_dora: bool = False,
) -> bool:
self._peft_config = {
"use_lora": bool(use_lora),
@ -462,6 +467,7 @@ class _MLXTrainerAdapter:
"gradient_checkpointing": use_gradient_checkpointing,
"use_rslora": bool(use_rslora),
"use_loftq": bool(use_loftq),
"use_dora": bool(use_dora),
"finetune_vision_layers": bool(finetune_vision_layers),
"finetune_language_layers": bool(finetune_language_layers),
"finetune_attention_modules": bool(finetune_attention_modules),
@ -569,6 +575,7 @@ class _MLXTrainerAdapter:
"gradient_checkpointing": "unsloth",
"use_rslora": False,
"use_loftq": False,
"use_dora": False,
"finetune_vision_layers": True,
"finetune_language_layers": True,
"finetune_attention_modules": True,

26
studio/backend/core/training/worker.py
View file

@ -764,8 +764,8 @@ def _rocm_classify_unified_memory(props: Any) -> tuple[str, bool]:
- ``gcn_arch``: canonical arch string (e.g. ``"gfx1151"``) when a known
attribute is present, else ``""``.
- ``is_unified``: ``True`` for AMD APUs with a shared GPU/system-RAM pool
(gfx1150 Strix Point, gfx1151 Strix Halo) — these need a lower
``set_per_process_memory_fraction`` cap to leave OS headroom.
(gfx1150 Strix Point, gfx1151 Strix Halo, gfx1152 Krackan Point) — these
need a lower ``set_per_process_memory_fraction`` cap to leave OS headroom.
Classification priority:
1. ``props.is_integrated`` truthy (hipDeviceProp_t.integrated -- the
@ -778,6 +778,7 @@ def _rocm_classify_unified_memory(props: Any) -> tuple[str, bool]:
- gfx1151 Strix Halo / Gorgon Halo: ``Radeon 8065S`` (Ryzen AI
Max+ 495), ``Radeon 8060S`` (Ryzen AI MAX+
395), ``Radeon 8050S`` (cut-down SKU)
- gfx1152 Krackan Point: ``Radeon 860M``, ``Radeon 840M``
"""
gcn_arch = ""
for _attr in ("gcnArchName", "gcn_arch_name", "arch_name", "gfx_arch_name"):
@ -797,9 +798,13 @@ def _rocm_classify_unified_memory(props: Any) -> tuple[str, bool]:
return gcn_arch, True
if gcn_arch:
return gcn_arch, gcn_arch in {"gfx1150", "gfx1151"}
# gfx1152 is Krackan Point, the third RDNA 3.5 APU: same shared
# GPU/system-RAM pool as Strix Point (gfx1150) and Strix Halo (gfx1151).
return gcn_arch, gcn_arch in {"gfx1150", "gfx1151", "gfx1152"}
# Arch attrs absent — fall back to device-name matching.
# Arch attrs absent — fall back to device-name matching. Only reached under
# _hw.IS_ROCM, so the NVIDIA GeForce 840M cannot collide with the Krackan
# markers here.
dev_lower = (getattr(props, "name", "") or "").lower()
is_unified = (
"890m" in dev_lower
@ -807,6 +812,8 @@ def _rocm_classify_unified_memory(props: Any) -> tuple[str, bool]:
or "8065s" in dev_lower
or "8060s" in dev_lower
or "8050s" in dev_lower
or "860m" in dev_lower
or "840m" in dev_lower
)
return gcn_arch, is_unified
@ -1547,6 +1554,10 @@ def _run_mlx_training(event_queue, stop_queue, config):
message = "LoftQ is not supported for MLX training yet."
_send("error", error = message)
raise NotImplementedError(message)
if config.get("use_dora"):
message = "DoRA is not supported for MLX training yet."
_send("error", error = message)
raise NotImplementedError(message)
if config.get("is_embedding"):
message = "Embedding model training is not supported for MLX training yet."
_send("error", error = message)
@ -2373,7 +2384,7 @@ def run_training_process(*, event_queue: Any, stop_queue: Any, config: dict) ->
env = os.getenv("ENVIRONMENT_TYPE", "production"),
)
apply_gpu_ids(config.get("resolved_gpu_ids"))
apply_gpu_ids(config.get("resolved_gpu_ids"), backend = config.get("device_backend"))
model_name = config["model_name"]
@ -2824,7 +2835,7 @@ def run_training_process(*, event_queue: Any, stop_queue: Any, config: dict) ->
# On ROCm, exhausting VRAM can hang the HIP driver instead of raising.
# set_per_process_memory_fraction caps the allocator so PyTorch raises
# OutOfMemoryError first (NVIDIA already has a graceful OOM path).
# Unified-memory APUs (gfx1150/gfx1151) share GPU+system RAM, so use 0.80
# Unified-memory APUs (gfx1150/gfx1151/gfx1152) share GPU+system RAM, so use 0.80
# vs 0.90 for discrete. Classify via gcnArchName, else device-name markers.
# Non-fatal: skipped if torch is not importable.
if _hw.IS_ROCM:
@ -3186,6 +3197,7 @@ def run_training_process(*, event_queue: Any, stop_queue: Any, config: dict) ->
use_gradient_checkpointing = config.get("gradient_checkpointing", "unsloth"),
use_rslora = config.get("use_rslora", False),
use_loftq = config.get("use_loftq", False),
use_dora = config.get("use_dora", False),
)
elif use_lora:
_send_status(event_queue, "Configuring LoRA adapters...")
@ -3202,6 +3214,7 @@ def run_training_process(*, event_queue: Any, stop_queue: Any, config: dict) ->
use_gradient_checkpointing = config.get("gradient_checkpointing", "unsloth"),
use_rslora = config.get("use_rslora", False),
use_loftq = config.get("use_loftq", False),
use_dora = config.get("use_dora", False),
)
else:
_send_status(event_queue, "Preparing model for full finetuning...")
@ -3630,6 +3643,7 @@ def _run_embedding_training(event_queue: Any, stop_queue: Any, config: dict) ->
use_gradient_checkpointing = gradient_checkpointing,
random_state = config.get("random_seed", 3407),
use_rslora = config.get("use_rslora", False),
use_dora = config.get("use_dora", False),
loftq_config = {"loftq_bits": 4, "loftq_iter": 1}
if config.get("use_loftq")
else None,

6
studio/backend/main.py
View file

@ -438,7 +438,11 @@ def _run_llama_cpp_startup_probes(app: FastAPI) -> None:
import structlog as _structlog
_log = _structlog.get_logger(__name__)
if _caps.get("found") and not _caps.get("supports_mtp"):
if (
_caps.get("found")
and not _caps.get("supports_mtp")
and not _caps.get("mtp_probe_inconclusive")
):
_msg = (
"llama.cpp prebuilt lacks MTP support "
"(--spec-type mtp/draft-mtp). Run `unsloth studio update`. "

84
studio/backend/models/inference.py
View file

@ -70,11 +70,23 @@ class LoadRequest(BaseModel):
cache_type_kv: Optional[str] = Field(
None,
description = "KV cache data type for both K and V (e.g. 'f16', 'bf16', 'q8_0', 'q4_1', 'q5_1')",
description = (
"KV cache data type for both K and V "
"(e.g. 'f16', 'bf16', 'q8_0', 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'iq4_nl', 'f32')"
),
)
gpu_ids: Optional[List[int]] = Field(
None,
description = "Physical GPU indices to use, for example [0, 1]. Omit or pass [] to use automatic selection. Explicit gpu_ids are unsupported when the parent CUDA_VISIBLE_DEVICES uses UUID/MIG entries. For GGUF models the picked devices are pinned via CUDA/HIP_VISIBLE_DEVICES.",
description = (
"GPU placement pool, for example [0, 1]. Omit or pass [] to use "
"automatic selection. CUDA/ROCm and Intel XPU values are physical "
"GPU indices; Vulkan values are ggml device ordinals. Explicit "
"physical IDs are unsupported when the parent visibility mask uses "
"non-numeric or subdevice entries, including CUDA_VISIBLE_DEVICES "
"with UUID/MIG entries and ZE_AFFINITY_MASK with subdevice tokens "
"(for example '0.0,0.1') or FLAT-hierarchy tile handles. For GGUF "
"models the fitter may pin the smallest subset of this pool that fits."
),
)
speculative_type: Optional[str] = Field(
None,
@ -433,7 +445,10 @@ class LoadResponse(BaseModel):
)
cache_type_kv: Optional[str] = Field(
None,
description = "KV cache data type for K and V (e.g. 'f16', 'bf16', 'q8_0')",
description = (
"KV cache data type for K and V "
"(e.g. 'f16', 'bf16', 'q8_0', 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'iq4_nl', 'f32')"
),
)
chat_template: Optional[str] = Field(
None,
@ -485,7 +500,14 @@ class LoadResponse(BaseModel):
)
gpu_ids: Optional[List[int]] = Field(
None,
description = "Physical GPU indices the model is pinned to, or None for automatic selection.",
description = "Effective GPU indices the model is using after fit-time narrowing, or None for automatic selection.",
)
requested_gpu_ids: Optional[List[int]] = Field(
None,
description = (
"GPU placement pool requested by the user before fit-time narrowing, "
"or None for automatic selection."
),
)
@ -586,7 +608,11 @@ class InferenceStatusResponse(BaseModel):
)
cache_type_kv: Optional[str] = Field(
None,
description = "KV cache quantization dtype (e.g. 'q8_0'), or None for default",
description = (
"KV cache quantization dtype "
"(e.g. 'f16', 'bf16', 'q8_0', 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'iq4_nl', 'f32'), "
"or None for default"
),
)
chat_template: Optional[str] = Field(
None, description = "Model's default chat template (Jinja2 source), if any"
@ -649,7 +675,14 @@ class InferenceStatusResponse(BaseModel):
)
gpu_ids: Optional[List[int]] = Field(
None,
description = "Physical GPU indices the model is pinned to, or None for automatic selection.",
description = "Effective GPU indices the model is using after fit-time narrowing, or None for automatic selection.",
)
requested_gpu_ids: Optional[List[int]] = Field(
None,
description = (
"GPU placement pool requested by the user before fit-time narrowing, "
"or None for automatic selection."
),
)
llama_cpp_supports_mtp: bool = Field(
True,
@ -886,11 +919,11 @@ class ThinkingConfig(BaseModel):
# Recognized permission_mode values. The field accepts a plain string rather than
# a Literal so an unrecognized value from a newer UI/client degrades to the
# safest gate ("ask") instead of a 422; the tool loops apply the same unknown ->
# ask fallback, so normalizing here keeps that forward-compat path reachable at
# the API boundary. None stays unset ("behaves as 'ask'" without self-enabling
# the confirm gate).
# a Literal so an unrecognized value from a newer UI/client degrades to the safest
# gate ("ask") instead of a 422. None stays unset at the request boundary: the tool
# loops normalize it to the product default "auto", while the route's confirm-gate
# derivation keeps an unset mode lenient (a non-streaming request cannot prompt, so
# it runs) to keep non-streaming clients and health checks working.
_KNOWN_PERMISSION_MODES = ("ask", "auto", "off", "full")
@ -1053,11 +1086,13 @@ class ChatCompletionRequest(BaseModel):
"[x-unsloth] Permission level for local tool calls. 'ask' pauses every "
"call for approval; 'ask'/'auto' enable the confirmation gate on their "
"own (needs a streaming request to deliver prompts). 'auto' ('Approve for "
"me') only pauses calls detected as potentially unsafe (state-mutating "
"terminal/python/MCP calls); read-only calls run immediately, and the "
"sandbox stays on. 'full' is equivalent to bypass_permissions=true (no "
"confirmation, no sandbox). Unset behaves as 'ask'. An unrecognized value "
"(e.g. from a newer client) is treated as 'ask'."
"me') only pauses calls detected as high risk (credential reads, privilege "
"escalation, destructive/persistence, network exfil); ordinary calls run "
"immediately, and the sandbox stays on. 'full' is equivalent to "
"bypass_permissions=true (no confirmation, no sandbox). Unset defaults to "
"'auto' for the per-call gate; a non-streaming request without an explicit "
"mode cannot prompt and runs the loop. An unrecognized value (e.g. from a "
"newer client) is treated as 'ask'."
),
)
auto_heal_tool_calls: Optional[bool] = Field(
@ -1343,6 +1378,21 @@ class ChatCompletionRequest(BaseModel):
elif self.permission_mode == "off":
# "Off" never prompts, so route guards must see confirm disabled.
self.confirm_tool_calls = False
elif (
self.permission_mode is None
and self.confirm_tool_calls is True
and not (self.provider_id or self.provider_type)
):
# An explicit confirm_tool_calls=True with no mode opted into the
# pre-permission-mode contract of gating every call, so resolve it to
# "ask" rather than let the loop apply the "auto" default, which would
# silently weaken that opt-in to high-risk calls only. Unlike the "ask"
# branch below this only sets permission_mode, which is inert unless
# Unsloth's own tool loop runs, so it needs no enable_tools/mcp gate --
# deliberate, since a process-wide --enable-tools policy can force the
# loop when the request sets neither flag. A bare unset request
# (confirm_tool_calls is None) still defaults to auto.
self.permission_mode = "ask"
elif (
self.permission_mode == "ask"
and self.confirm_tool_calls is None
@ -2026,7 +2076,7 @@ class AnthropicMessagesRequest(BaseModel):
)
permission_mode: Optional[str] = Field(
None,
description = "[x-unsloth] Permission level for local tool calls: 'ask' pauses every call, 'auto' only pauses calls detected as potentially unsafe, 'off' never pauses (sandbox stays on), 'full' equals bypass_permissions=true. Unset behaves as 'ask'; an unrecognized value (e.g. from a newer client) is treated as 'ask'. Declared explicitly so omitted requests default to None instead of raising AttributeError.",
description = "[x-unsloth] Permission level for local tool calls: 'ask' pauses every call, 'auto' ('Approve for me') only pauses calls detected as high risk, 'off' never pauses (sandbox stays on), 'full' equals bypass_permissions=true. Unset defaults to 'auto' for the per-call gate; a non-streaming request without an explicit mode runs the loop. An unrecognized value (e.g. from a newer client) is treated as 'ask'. Declared explicitly so omitted requests default to None instead of raising AttributeError.",
)
auto_heal_tool_calls: Optional[bool] = Field(
True,

Some files were not shown because too many files have changed in this diff Show more