soup/docs/models.md

85 lines
4.9 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Supported Models & Optional Extras
[← Back to the Soup README](../README.md)
> Recommended model families, the VRAM size guide, and the pip extras matrix.
## Supported Models
Soup works with **any** of the **340,000+** text-generation models on [HuggingFace Hub](https://huggingface.co/models?pipeline_tag=text-generation). If a model supports `AutoModelForCausalLM`, it works with Soup — zero config changes needed.
### Recommended Models
| Model Family | Models | Sizes | Best For |
|---|---|---|---|
| **Llama 4** | Llama-4-Scout-17B, Llama-4-Maverick-17B | 17B | General, multilingual |
| **Llama 3.x** | Llama-3.1-8B-Instruct, Llama-3.3-70B-Instruct | 1B70B | Chat, instruction following |
| **Llama 3.2 Vision** | Llama-3.2-11B-Vision-Instruct, Llama-3.2-90B-Vision | 11B90B | Image understanding |
| **Gemma 3** | Gemma-3-4B-IT, Gemma-3-9B-IT, Gemma-3-27B-IT | 4B27B | Efficient, multilingual |
| **Qwen 3** | Qwen3-8B, Qwen3-14B, Qwen3-32B, Qwen3-235B-A22B | 0.6B235B | Reasoning, code, MoE |
| **Qwen 2.5** | Qwen2.5-7B-Instruct, Qwen2.5-Coder-32B-Instruct | 0.5B72B | Code, math |
| **DeepSeek** | DeepSeek-R1-Distill-Llama-8B, DeepSeek-V3-0324 | 1.5B671B | Reasoning (GRPO), code |
| **Phi-4** | Phi-4-14B, Phi-4-mini-reasoning | 3.8B14B | Compact reasoning |
| **Mistral** | Mistral-7B-Instruct-v0.3, Mistral-Small-24B-Instruct | 7B24B | Fast, efficient |
| **Mixtral** | Mixtral-8x7B-Instruct-v0.1, Mixtral-8x22B | 47B141B | MoE architecture |
| **CodeLlama** | CodeLlama-7b-Instruct-hf, CodeLlama-34b-Instruct | 7B34B | Code generation |
| **StarCoder 2** | StarCoder2-15B, StarCoder2-7B | 3B15B | Code completion |
| **Yi** | Yi-1.5-34B-Chat, Yi-1.5-9B-Chat | 6B34B | Multilingual chat |
| **InternLM 3** | InternLM3-8B-Instruct | 8B | Chinese + English |
| **Falcon** | Falcon-11B, Falcon-40B-Instruct | 7B180B | Open-weight |
### Vision Models (with `modality: vision`)
| Model | Size | Supported Formats |
|---|---|---|
| LLaMA-3.2-11B-Vision-Instruct | 11B | LLaVA, ShareGPT4V |
| Qwen2-VL-7B-Instruct | 7B | LLaVA, ShareGPT4V |
| Pixtral-12B-2409 | 12B | LLaVA, ShareGPT4V |
### Quick Size Guide
| VRAM | Max Model (QLoRA 4-bit) | Example |
|---|---|---|
| 8 GB | ~7B | Llama-3.1-8B, Mistral-7B |
| 16 GB | ~14B | Phi-4-14B, Qwen2.5-14B |
| 24 GB | ~34B | CodeLlama-34B, Yi-1.5-34B |
| 48 GB | ~70B | Llama-3.3-70B |
| 80 GB+ | 70B+ (full) or MoE | Mixtral-8x22B, DeepSeek-V3 |
> **Note:** Soup auto-detects your GPU and estimates the optimal batch size. Use `soup doctor` to check your setup.
## Optional Extras
The core `pip install soup-cli` is a light install — the CLI, config system, and data tools, with
no PyTorch. Add `[train]` to fine-tune, or install other extras only when you need them:
| Extra | Install | What it adds |
|---|---|---|
| `train` | `pip install 'soup-cli[train]'` | Training stack: torch, transformers, peft, trl, datasets, bitsandbytes, accelerate |
| `all` | `pip install 'soup-cli[all]'` | `train` + `serve` + `ui` + `data` in one shot |
| `fast` | `pip install 'soup-cli[fast]'` | Unsloth backend (2-5x faster, lower VRAM) |
| `vision` | `pip install 'soup-cli[vision]'` | Vision / multimodal fine-tuning (Pillow) |
| `audio` | `pip install 'soup-cli[audio]'` | Audio / speech fine-tuning (librosa, soundfile) |
| `mlx` | `pip install 'soup-cli[mlx]'` | Apple Silicon backend (mlx, mlx-lm) |
| `qat` | `pip install 'soup-cli[qat]'` | Quantization-Aware Training (torchao) |
| `serve` | `pip install 'soup-cli[serve]'` | Inference server (FastAPI + uvicorn) |
| `serve-fast` | `pip install 'soup-cli[serve-fast]'` | vLLM inference backend (2-4x throughput) |
| `sglang` | `pip install 'soup-cli[sglang]'` | SGLang inference backend |
| `ui` | `pip install 'soup-cli[ui]'` | Web UI + inference server |
| `tui` | `pip install 'soup-cli[tui]'` | Full-screen Textual dashboard (`soup tui`) |
| `eval` | `pip install 'soup-cli[eval]'` | Benchmark evaluation (lm-evaluation-harness) |
| `data` | `pip install 'soup-cli[data]'` | Deduplication (MinHash via datasketch) |
| `data-pro` | `pip install 'soup-cli[data-pro]'` | Language detection + PII (langdetect, presidio) |
| `deepspeed` | `pip install 'soup-cli[deepspeed]'` | Multi-GPU training (DeepSpeed ZeRO) |
| `liger` | `pip install 'soup-cli[liger]'` | Liger Kernel fused ops |
| `ring-attn` | `pip install 'soup-cli[ring-attn]'` | Ring FlashAttention (sequence parallelism) |
| `onnx` / `tensorrt` | `pip install 'soup-cli[onnx]'` | ONNX / TensorRT-LLM export |
| `awq` / `gptq` | `pip install 'soup-cli[awq]'` | AWQ / GPTQ quantized export |
| `trackers` | `pip install 'soup-cli[trackers]'` | MLflow / SwanLab / Trackio logging |
| `remote` | `pip install 'soup-cli[remote]'` | Remote datasets (s3 / gs / az / oci) |
| `dev` | `pip install 'soup-cli[dev]'` | Tests + lint + types (pytest, ruff, mypy, pre-commit) |
The complete, authoritative extras list is in [`pyproject.toml`](../pyproject.toml).