Merge branch 'main' into release/2.5

Author: Jintao-Huang

README.md

@@ -36,7 +36,7 @@
 - [Citation](#-citation)
 
 ## 📝 Introduction
-SWIFT supports training(PreTraining/Fine-tuning/RLHF), inference, evaluation and deployment of **350+ LLMs and 90+ MLLMs** (multimodal large models). Developers can directly apply our framework to their own research and production environments to realize the complete workflow from model training and evaluation to application. In addition to supporting the lightweight training solutions provided by [PEFT](https://github.com/huggingface/peft), we also provide a complete **Adapters library** to support the latest training techniques such as NEFTune, LoRA+, LLaMA-PRO, etc. This adapter library can be used directly in your own custom workflow without our training scripts.
+SWIFT supports training(PreTraining/Fine-tuning/RLHF), inference, evaluation and deployment of **350+ LLMs and 100+ MLLMs** (multimodal large models). Developers can directly apply our framework to their own research and production environments to realize the complete workflow from model training and evaluation to application. In addition to supporting the lightweight training solutions provided by [PEFT](https://github.com/huggingface/peft), we also provide a complete **Adapters library** to support the latest training techniques such as NEFTune, LoRA+, LLaMA-PRO, etc. This adapter library can be used directly in your own custom workflow without our training scripts.
 
 To facilitate use by users unfamiliar with deep learning, we provide a Gradio web-ui for controlling training and inference, as well as accompanying deep learning courses and best practices for beginners. SWIFT web-ui is available both on [Huggingface space](https://huggingface.co/spaces/tastelikefeet/swift) and [ModelScope studio](https://www.modelscope.cn/studios/iic/Scalable-lightWeight-Infrastructure-for-Fine-Tuning/summary), please feel free to try!
 
@@ -55,6 +55,7 @@ You can contact us and communicate with us by adding our group:
 <img src="asset/discord_qr.jpg" width="200" height="200">  |  <img src="asset/wechat.png" width="200" height="200">
 
 ## 🎉 News
+- 2024.10.09: Support for training and deploying ovis1.6-gemma2 series models. Experience it using `swift infer --model_type ovis1_6-gemma2-9b`.
 - 2024.09.26: Support for training and deploying llama3.2-vision series models. Experience it using `swift infer --model_type llama3_2-11b-vision-instruct`.
 - 2024.09.26: Support for training and deploying llama3.2 series models. Experience it using `swift infer --model_type llama3_2-1b-instruct`.
 - 2024.09.25: Support for training to deployment with got-ocr2. Best practices can be found [here](https://github.com/modelscope/ms-swift/issues/2122).
@@ -642,6 +643,7 @@ The complete list of supported models and datasets can be found at [Supported Mo
 | Idefics3                                                   | [HuggingFaceM4](https://huggingface.co/HuggingFaceM4)                               | English       | 8B      | chat model       |
 | Pixtral                                | [mistralai](https://huggingface.co/mistralai)                     | English       | 12B      | chat model       |
 | Llama3.1-Omni              | [LLaMA-Omni](https://github.com/ictnlp/LLaMA-Omni)                | English       | 8B      | chat model       |
+| Ovis              | [Ovis](https://github.com/AIDC-AI/Ovis)                | English       | 9B      | chat model       |
 
 
 #### Diffusion Models

README_CN.md

@@ -37,7 +37,7 @@
 - [引用](#-引用)
 
 ## 📝 简介
-SWIFT支持**350+ LLM和90+ MLLM**（多模态大模型）的训练(预训练、微调、对齐)、推理、评测和部署。开发者可以直接将我们的框架应用到自己的Research和生产环境中，实现模型训练评测到应用的完整链路。我们除支持了[PEFT](https://github.com/huggingface/peft)提供的轻量训练方案外，也提供了一个完整的**Adapters库**以支持最新的训练技术，如NEFTune、LoRA+、LLaMA-PRO等，这个适配器库可以脱离训练脚本直接使用在自己的自定流程中。
+SWIFT支持**350+ LLM和100+ MLLM**（多模态大模型）的训练(预训练、微调、对齐)、推理、评测和部署。开发者可以直接将我们的框架应用到自己的Research和生产环境中，实现模型训练评测到应用的完整链路。我们除支持了[PEFT](https://github.com/huggingface/peft)提供的轻量训练方案外，也提供了一个完整的**Adapters库**以支持最新的训练技术，如NEFTune、LoRA+、LLaMA-PRO等，这个适配器库可以脱离训练脚本直接使用在自己的自定流程中。
 
 为方便不熟悉深度学习的用户使用，我们提供了一个Gradio的web-ui用于控制训练和推理，并提供了配套的深度学习课程和最佳实践供新手入门。 可以在[Huggingface space](https://huggingface.co/spaces/tastelikefeet/swift) 和 [ModelScope创空间](https://www.modelscope.cn/studios/iic/Scalable-lightWeight-Infrastructure-for-Fine-Tuning/summary) 中体验SWIFT web-ui功能了。
 
@@ -56,6 +56,7 @@ SWIFT具有丰富全面的文档，请查看我们的文档网站:
 
 
 ## 🎉 新闻
+- 2024.10.09: 支持ovis1.6-gemma2的训练到部署. 使用`swift infer --model_type ovis1_6-gemma2-9b`进行体验.
 - 2024.09.26: 支持llama3.2-vision系列模型的训练到部署. 使用`swift infer --model_type llama3_2-11b-vision-instruct`进行体验.
 - 2024.09.26: 支持llama3.2系列模型的训练到部署. 使用`swift infer --model_type llama3_2-1b-instruct`进行体验.
 - 2024.09.25: 支持got-ocr2的训练到部署. 最佳实践可以查看[这里](https://github.com/modelscope/ms-swift/issues/2122).
@@ -635,6 +636,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
 | Idefics3                                | [HuggingFaceM4](https://huggingface.co/HuggingFaceM4)                               | 英文       | 8B      | chat模型       |
 | Pixtral                                | [mistralai](https://huggingface.co/mistralai)                               | 英文       | 12B      | chat模型       |
 | Llama3.1-Omni              | [LLaMA-Omni](https://github.com/ictnlp/LLaMA-Omni)                | 英文       | 8B      | chat模型       |
+| Ovis              | [Ovis](https://github.com/AIDC-AI/Ovis)                | 英文       | 9B      | chat模型       |
 
 
 #### 扩散模型

docs/source/Instruction/支持的模型和数据集.md

@@ -405,8 +405,9 @@
 |mamba-2.8b|[AI-ModelScope/mamba-2.8b-hf](https://modelscope.cn/models/AI-ModelScope/mamba-2.8b-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|✘|✘|✘|✘|transformers>=4.39.0|-|[state-spaces/mamba-2.8b-hf](https://huggingface.co/state-spaces/mamba-2.8b-hf)|
 |telechat-7b|[TeleAI/TeleChat-7B](https://modelscope.cn/models/TeleAI/TeleChat-7B/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/telechat-7B](https://huggingface.co/Tele-AI/telechat-7B)|
 |telechat-12b|[TeleAI/TeleChat-12B](https://modelscope.cn/models/TeleAI/TeleChat-12B/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B](https://huggingface.co/Tele-AI/TeleChat-12B)|
-|telechat-12b-v2|[TeleAI/TeleChat-12B-v2](https://modelscope.cn/models/TeleAI/TeleChat-12B-v2/summary)|key_value, query|telechat-v2|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B-v2](https://huggingface.co/Tele-AI/TeleChat-12B-v2)|
-|telechat-12b-v2-gptq-int4|[swift/TeleChat-12B-V2-GPTQ-Int4](https://modelscope.cn/models/swift/TeleChat-12B-V2-GPTQ-Int4/summary)|key_value, query|telechat-v2|✔|✘|✘|✘|auto_gptq>=0.5|-|-|
+|telechat-12b-v2|[TeleAI/TeleChat-12B-v2](https://modelscope.cn/models/TeleAI/TeleChat-12B-v2/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B-v2](https://huggingface.co/Tele-AI/TeleChat-12B-v2)|
+|telechat-12b-v2-gptq-int4|[swift/TeleChat-12B-V2-GPTQ-Int4](https://modelscope.cn/models/swift/TeleChat-12B-V2-GPTQ-Int4/summary)|key_value, query|telechat|✔|✘|✘|✘|auto_gptq>=0.5|-|-|
+|telechat2-115b|[TeleAI/TeleChat2-115B](https://modelscope.cn/models/TeleAI/TeleChat2-115B/summary)|key_value, query|telechat2|✔|✘|✘|✘||-|[Tele-AI/TeleChat2-115B](https://huggingface.co/Tele-AI/TeleChat2-115B)|
 |grok-1|[colossalai/grok-1-pytorch](https://modelscope.cn/models/colossalai/grok-1-pytorch/summary)|q_proj, k_proj, v_proj|default-generation|✘|✘|✘|✘||-|[hpcai-tech/grok-1](https://huggingface.co/hpcai-tech/grok-1)|
 |dbrx-instruct|[AI-ModelScope/dbrx-instruct](https://modelscope.cn/models/AI-ModelScope/dbrx-instruct/summary)|attn.Wqkv|dbrx|✔|✔|✘|✘|transformers>=4.36|moe|[databricks/dbrx-instruct](https://huggingface.co/databricks/dbrx-instruct)|
 |dbrx-base|[AI-ModelScope/dbrx-base](https://modelscope.cn/models/AI-ModelScope/dbrx-base/summary)|attn.Wqkv|dbrx|✔|✔|✘|✘|transformers>=4.36|moe|[databricks/dbrx-base](https://huggingface.co/databricks/dbrx-base)|
@@ -492,6 +493,7 @@
 |internvl2-llama3-76b-awq|[OpenGVLab/InternVL2-Llama3-76B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL2-Llama3-76B-AWQ/summary)|^(language_model\|mlp1)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|internvl2|✔|✔|✔|✘|transformers>=4.36, timm|vision, video|[OpenGVLab/InternVL2-Llama3-76B-AWQ](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B-AWQ)|
 |deepseek-vl-1_3b-chat|[deepseek-ai/deepseek-vl-1.3b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat/summary)|^(language_model\|aligner)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|deepseek-vl|✔|✘|✔|✘||vision|[deepseek-ai/deepseek-vl-1.3b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-1.3b-chat)|
 |deepseek-vl-7b-chat|[deepseek-ai/deepseek-vl-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat/summary)|^(language_model\|aligner)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|deepseek-vl|✔|✘|✔|✘||vision|[deepseek-ai/deepseek-vl-7b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat)|
+|ovis1_6-gemma2-9b|[AIDC-AI/Ovis1.6-Gemma2-9B](https://modelscope.cn/models/AIDC-AI/Ovis1.6-Gemma2-9B/summary)|^(llm)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|ovis1_6|✔|✘|✘|✘|transformers>=4.42|vision|[AIDC-AI/Ovis1.6-Gemma2-9B](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B)|
 |paligemma-3b-pt-224|[AI-ModelScope/paligemma-3b-pt-224](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-224/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224)|
 |paligemma-3b-pt-448|[AI-ModelScope/paligemma-3b-pt-448](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-448/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-448](https://huggingface.co/google/paligemma-3b-pt-448)|
 |paligemma-3b-pt-896|[AI-ModelScope/paligemma-3b-pt-896](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-896/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-896](https://huggingface.co/google/paligemma-3b-pt-896)|

docs/source_en/Instruction/Supported-models-datasets.md

@@ -405,8 +405,9 @@ The table below introcudes all models supported by SWIFT:
 |mamba-2.8b|[AI-ModelScope/mamba-2.8b-hf](https://modelscope.cn/models/AI-ModelScope/mamba-2.8b-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|✘|✘|✘|✘|transformers>=4.39.0|-|[state-spaces/mamba-2.8b-hf](https://huggingface.co/state-spaces/mamba-2.8b-hf)|
 |telechat-7b|[TeleAI/TeleChat-7B](https://modelscope.cn/models/TeleAI/TeleChat-7B/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/telechat-7B](https://huggingface.co/Tele-AI/telechat-7B)|
 |telechat-12b|[TeleAI/TeleChat-12B](https://modelscope.cn/models/TeleAI/TeleChat-12B/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B](https://huggingface.co/Tele-AI/TeleChat-12B)|
-|telechat-12b-v2|[TeleAI/TeleChat-12B-v2](https://modelscope.cn/models/TeleAI/TeleChat-12B-v2/summary)|key_value, query|telechat-v2|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B-v2](https://huggingface.co/Tele-AI/TeleChat-12B-v2)|
-|telechat-12b-v2-gptq-int4|[swift/TeleChat-12B-V2-GPTQ-Int4](https://modelscope.cn/models/swift/TeleChat-12B-V2-GPTQ-Int4/summary)|key_value, query|telechat-v2|✔|✘|✘|✘|auto_gptq>=0.5|-|-|
+|telechat-12b-v2|[TeleAI/TeleChat-12B-v2](https://modelscope.cn/models/TeleAI/TeleChat-12B-v2/summary)|key_value, query|telechat|✔|✘|✘|✘||-|[Tele-AI/TeleChat-12B-v2](https://huggingface.co/Tele-AI/TeleChat-12B-v2)|
+|telechat-12b-v2-gptq-int4|[swift/TeleChat-12B-V2-GPTQ-Int4](https://modelscope.cn/models/swift/TeleChat-12B-V2-GPTQ-Int4/summary)|key_value, query|telechat|✔|✘|✘|✘|auto_gptq>=0.5|-|-|
+|telechat2-115b|[TeleAI/TeleChat2-115B](https://modelscope.cn/models/TeleAI/TeleChat2-115B/summary)|key_value, query|telechat2|✔|✘|✘|✘||-|[Tele-AI/TeleChat2-115B](https://huggingface.co/Tele-AI/TeleChat2-115B)|
 |grok-1|[colossalai/grok-1-pytorch](https://modelscope.cn/models/colossalai/grok-1-pytorch/summary)|q_proj, k_proj, v_proj|default-generation|✘|✘|✘|✘||-|[hpcai-tech/grok-1](https://huggingface.co/hpcai-tech/grok-1)|
 |dbrx-instruct|[AI-ModelScope/dbrx-instruct](https://modelscope.cn/models/AI-ModelScope/dbrx-instruct/summary)|attn.Wqkv|dbrx|✔|✔|✘|✘|transformers>=4.36|moe|[databricks/dbrx-instruct](https://huggingface.co/databricks/dbrx-instruct)|
 |dbrx-base|[AI-ModelScope/dbrx-base](https://modelscope.cn/models/AI-ModelScope/dbrx-base/summary)|attn.Wqkv|dbrx|✔|✔|✘|✘|transformers>=4.36|moe|[databricks/dbrx-base](https://huggingface.co/databricks/dbrx-base)|
@@ -492,6 +493,7 @@ The table below introcudes all models supported by SWIFT:
 |internvl2-llama3-76b-awq|[OpenGVLab/InternVL2-Llama3-76B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL2-Llama3-76B-AWQ/summary)|^(language_model\|mlp1)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|internvl2|✔|✔|✔|✘|transformers>=4.36, timm|vision, video|[OpenGVLab/InternVL2-Llama3-76B-AWQ](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B-AWQ)|
 |deepseek-vl-1_3b-chat|[deepseek-ai/deepseek-vl-1.3b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat/summary)|^(language_model\|aligner)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|deepseek-vl|✔|✘|✔|✘||vision|[deepseek-ai/deepseek-vl-1.3b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-1.3b-chat)|
 |deepseek-vl-7b-chat|[deepseek-ai/deepseek-vl-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat/summary)|^(language_model\|aligner)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|deepseek-vl|✔|✘|✔|✘||vision|[deepseek-ai/deepseek-vl-7b-chat](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat)|
+|ovis1_6-gemma2-9b|[AIDC-AI/Ovis1.6-Gemma2-9B](https://modelscope.cn/models/AIDC-AI/Ovis1.6-Gemma2-9B/summary)|^(llm)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|ovis1_6|✔|✘|✘|✘|transformers>=4.42|vision|[AIDC-AI/Ovis1.6-Gemma2-9B](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B)|
 |paligemma-3b-pt-224|[AI-ModelScope/paligemma-3b-pt-224](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-224/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224)|
 |paligemma-3b-pt-448|[AI-ModelScope/paligemma-3b-pt-448](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-448/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-448](https://huggingface.co/google/paligemma-3b-pt-448)|
 |paligemma-3b-pt-896|[AI-ModelScope/paligemma-3b-pt-896](https://modelscope.cn/models/AI-ModelScope/paligemma-3b-pt-896/summary)|^(language_model\|multi_modal_projector)(?!.\*(lm_head\|output\|emb\|wte\|shared)).\*|paligemma|✔|✔|✘|✘|transformers>=4.41|vision|[google/paligemma-3b-pt-896](https://huggingface.co/google/paligemma-3b-pt-896)|

swift/llm/deploy.py

@@ -275,7 +275,7 @@ async def inference_vllm_async(request: Union[ChatCompletionRequest, CompletionR
     request_id = request_info['request_id']
 
     kwargs = {'max_tokens': request.max_tokens}
-    for key in ['n', 'best_of', 'frequency_penalty', 'length_penalty', 'presence_penalty', 'num_beams']:
+    for key in ['n', 'best_of', 'frequency_penalty', 'length_penalty', 'presence_penalty']:
         kwargs[key] = getattr(request, key)
     for key in ['temperature', 'top_k', 'top_p', 'repetition_penalty']:
         new_value = getattr(request, key)
@@ -292,9 +292,6 @@ async def inference_vllm_async(request: Union[ChatCompletionRequest, CompletionR
             kwargs['logprobs'] = max(1, request.top_logprobs)
 
     generation_config = VllmGenerationConfig(**kwargs)
-    if generation_config.use_beam_search and request.stream:
-        error_msg = 'Streaming generation does not support beam search.'
-        raise ValueError(error_msg)
     tokenizer = template.tokenizer
     if tokenizer.eos_token is not None and tokenizer.eos_token not in generation_config.stop:
         generation_config.stop.append(tokenizer.eos_token)

swift/llm/export.py

@@ -255,18 +255,18 @@ def llm_export(args: ExportArguments) -> None:
         if args.quant_method == 'awq':
             from awq import AutoAWQForCausalLM
             model, template = prepare_model_template(
-                args, device_map=args.quant_device_map, verbose=False, automodel_class=AutoAWQForCausalLM)
+                args, device_map=args.quant_device_map, task='export', automodel_class=AutoAWQForCausalLM)
             awq_model_quantize(model, template.tokenizer, args.quant_batch_size)
             model.save_quantized(args.quant_output_dir)
         elif args.quant_method == 'gptq':
-            model, template = prepare_model_template(args, device_map=args.quant_device_map, verbose=False)
+            model, template = prepare_model_template(args, device_map=args.quant_device_map, task='export')
             gptq_quantizer = gptq_model_quantize(model, template.tokenizer, args.quant_batch_size)
             model.config.quantization_config.pop('dataset', None)
             gptq_quantizer.save(model, args.quant_output_dir)
         elif args.quant_method == 'bnb':
             args.quantization_bit = args.quant_bits
             args.bnb_4bit_compute_dtype, args.load_in_4bit, args.load_in_8bit = args.select_bnb()
-            model, template = prepare_model_template(args, device_map=args.quant_device_map, verbose=False)
+            model, template = prepare_model_template(args, device_map=args.quant_device_map, task='export')
             model.save_pretrained(args.quant_output_dir)
         else:
             raise ValueError(f'args.quant_method: {args.quant_method}')