eeffa4c065## Summary - Add web search tool calling for GGUF models (Search toggle, DuckDuckGo via ddgs) - Add KV cache dtype dropdown (f16/bf16/q8_0/q5_1/q4_1) in Chat Settings - Fix Qwen3/3.5 inference defaults per official docs (thinking on/off params) - Enable reasoning by default for Qwen3.5 4B and 9B - Replace "Generating" toast with inline spinner - Fix stop button via asyncio.to_thread (event loop no longer blocked) - Fix CUDA 12 compat lib paths for llama-server on CUDA 13 systems - Fix auto-load model name not appearing in selector - Training progress messages + dataset_num_proc fix Integrated PRs: - #4327 (imagineer99): BETA badge alignment (already in tree) - #4340 (Manan Shah): prioritize training models in model selection - #4344 (Roland Tannous): setup.sh macOS python version compatibility - #4345 (Manan Shah): revamp model+dataset checking logic
31 lines
973 B
Python
31 lines
973 B
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/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/Qwen3-4B-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() # ensure detect_hardware() has run
|
|
if hw.CHAT_ONLY:
|
|
return list(DEFAULT_MODELS_GGUF)
|
|
return list(DEFAULT_MODELS_STANDARD)
|