411c4d1e50* Add DeepSeek-V4-Flash-GGUF to Studio with none/high/max reasoning Adds unsloth/DeepSeek-V4-Flash-GGUF as a default selectable model with the recommended decoding defaults (temperature 1.0, top_p 1.0 from the official generation_config.json) and its three tier reasoning control. The high/max ladder is surfaced for deepseek-v4 model ids and flows through the existing enable_thinking_effort reasoning style via chat_template_kwargs, so no frontend changes are needed. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio DeepSeek-V4: segment-scope high, enable thinking for lone effort, render tests Match deepseek-v4 on whole repo-name segments so a future deepseek-v40 or deepseek40 cannot false-match the synthetic 'high'. In _request_reasoning_kwargs, emit enable_thinking when a named effort level is sent without it, so the newly exposed High mode renders thinking-on over the API (the UI already sent it explicitly). Add a none/high/max render-path test file (jinja behind importorskip) with a lone-high regression. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: danielhanchen <michaelhan2050@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
57 lines
1.9 KiB
Python
57 lines
1.9 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""Default model lists for inference, split by platform."""
|
|
|
|
import utils.hardware.hardware as hw
|
|
|
|
DEFAULT_MODELS_GGUF = [
|
|
"unsloth/Qwen3.6-27B-MTP-GGUF",
|
|
"unsloth/Qwen3.6-35B-A3B-MTP-GGUF",
|
|
"unsloth/DeepSeek-V4-Flash-GGUF",
|
|
"unsloth/gemma-4-E2B-it-GGUF",
|
|
"unsloth/gemma-4-E4B-it-GGUF",
|
|
"unsloth/gemma-4-31B-it-GGUF",
|
|
"unsloth/gemma-4-26B-A4B-it-GGUF",
|
|
"unsloth/Qwen3.5-4B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-9B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-35B-A3B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-0.8B-MTP-GGUF",
|
|
"unsloth/Llama-3.2-1B-Instruct-GGUF",
|
|
"unsloth/Llama-3.2-3B-Instruct-GGUF",
|
|
"unsloth/Llama-3.1-8B-Instruct-GGUF",
|
|
"unsloth/gemma-3-1b-it-GGUF",
|
|
"unsloth/gemma-3-4b-it-GGUF",
|
|
"unsloth/Qwen3-4B-GGUF",
|
|
]
|
|
|
|
DEFAULT_MODELS_STANDARD = [
|
|
"unsloth/Qwen3.6-27B-MTP-GGUF",
|
|
"unsloth/Qwen3.6-35B-A3B-MTP-GGUF",
|
|
"unsloth/DeepSeek-V4-Flash-GGUF",
|
|
"unsloth/gemma-4-E2B-it-GGUF",
|
|
"unsloth/gemma-4-E4B-it-GGUF",
|
|
"unsloth/gemma-4-31B-it-GGUF",
|
|
"unsloth/gemma-4-26B-A4B-it-GGUF",
|
|
"unsloth/Qwen3.5-4B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-9B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-35B-A3B-MTP-GGUF",
|
|
"unsloth/Qwen3.5-0.8B-MTP-GGUF",
|
|
"unsloth/gemma-4-E2B-it",
|
|
"unsloth/gemma-4-E4B-it",
|
|
"unsloth/gemma-4-31B-it",
|
|
"unsloth/gemma-4-26B-A4B-it",
|
|
"unsloth/Qwen3-4B-Instruct-2507",
|
|
"unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
|
|
"unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
|
|
"unsloth/Phi-3.5-mini-instruct",
|
|
"unsloth/Gemma-3-4B-it",
|
|
"unsloth/Qwen2-VL-2B-Instruct-bnb-4bit",
|
|
]
|
|
|
|
|
|
def get_default_models() -> list[str]:
|
|
hw.get_device() # ensures detect_hardware() has run
|
|
if hw.CHAT_ONLY:
|
|
return list(DEFAULT_MODELS_GGUF)
|
|
return list(DEFAULT_MODELS_STANDARD)
|