support cohere commandR #3184
This commit is contained in:
hiyouga
parent
7a8ae3f4ac
commit
e0dbac2845
|
|
@ -129,9 +129,10 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
|
|||
| Model | Model size | Default module | Template |
|
||||
| -------------------------------------------------------- | --------------------------- | ----------------- | --------- |
|
||||
| [Baichuan2](https://huggingface.co/baichuan-inc) | 7B/13B | W_pack | baichuan2 |
|
||||
| [BLOOM](https://huggingface.co/bigscience/bloom) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [BLOOMZ](https://huggingface.co/bigscience/bloomz) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b) | 6B | query_key_value | chatglm3 |
|
||||
| [BLOOM](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | query_key_value | chatglm3 |
|
||||
| [CommandR](https://huggingface.co/CohereForAI) | 35B/104B | q_proj,v_proj | cohere |
|
||||
| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B | q_proj,v_proj | deepseek |
|
||||
| [Falcon](https://huggingface.co/tiiuae) | 7B/40B/180B | query_key_value | falcon |
|
||||
| [Gemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma |
|
||||
|
|
@ -427,7 +428,7 @@ If you have a project that should be incorporated, please contact via email or c
|
|||
|
||||
This repository is licensed under the [Apache-2.0 License](LICENSE).
|
||||
|
||||
Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [CommandR](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -129,9 +129,10 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
|
|||
| 模型名 | 模型大小 | 默认模块 | Template |
|
||||
| -------------------------------------------------------- | --------------------------- | ----------------- | --------- |
|
||||
| [Baichuan2](https://huggingface.co/baichuan-inc) | 7B/13B | W_pack | baichuan2 |
|
||||
| [BLOOM](https://huggingface.co/bigscience/bloom) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [BLOOMZ](https://huggingface.co/bigscience/bloomz) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b) | 6B | query_key_value | chatglm3 |
|
||||
| [BLOOM](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - |
|
||||
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | query_key_value | chatglm3 |
|
||||
| [CommandR](https://huggingface.co/CohereForAI) | 35B/104B | q_proj,v_proj | cohere |
|
||||
| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B | q_proj,v_proj | deepseek |
|
||||
| [Falcon](https://huggingface.co/tiiuae) | 7B/40B/180B | query_key_value | falcon |
|
||||
| [Gemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma |
|
||||
|
|
@ -427,7 +428,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
|
|||
|
||||
本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。
|
||||
|
||||
使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [CommandR](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
|
||||
## 引用
|
||||
|
||||
|
|
|
|||
|
|
@ -1001,18 +1001,3 @@ register_model_group(
|
|||
},
|
||||
template="zephyr",
|
||||
)
|
||||
|
||||
|
||||
register_model_group(
|
||||
models={
|
||||
"Atom-7B": {
|
||||
DownloadSource.DEFAULT: "FlagAlpha/Atom-7B",
|
||||
DownloadSource.MODELSCOPE: "FlagAlpha/Atom-7B",
|
||||
},
|
||||
"Atom-7B-Chat": {
|
||||
DownloadSource.DEFAULT: "FlagAlpha/Atom-7B-Chat",
|
||||
DownloadSource.MODELSCOPE: "FlagAlpha/Atom-7B-Chat",
|
||||
},
|
||||
},
|
||||
template="atom",
|
||||
)
|
||||
|
|
|
|||
|
|
@ -55,7 +55,7 @@ class ModelArguments:
|
|||
)
|
||||
quantization_device_map: Optional[Literal["auto"]] = field(
|
||||
default=None,
|
||||
metadata={"help": "Device map used for loading the 4-bit quantized model, needs bitsandbytes>=0.43.0."},
|
||||
metadata={"help": "Device map used to infer the 4-bit quantized model, needs bitsandbytes>=0.43.0."},
|
||||
)
|
||||
rope_scaling: Optional[Literal["linear", "dynamic"]] = field(
|
||||
default=None,
|
||||
|
|
|
|||
|
|
@ -151,6 +151,9 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
|
|||
if training_args.do_train and training_args.predict_with_generate:
|
||||
raise ValueError("`predict_with_generate` cannot be set as True while training.")
|
||||
|
||||
if training_args.do_train and model_args.quantization_device_map == "auto":
|
||||
raise ValueError("Cannot use device map for quantized models in training.")
|
||||
|
||||
if finetuning_args.use_dora and model_args.use_unsloth:
|
||||
raise ValueError("Unsloth does not support DoRA.")
|
||||
|
||||
|
|
|
|||
|
|
@ -36,6 +36,7 @@ def load_tokenizer(model_args: "ModelArguments") -> "PreTrainedTokenizer":
|
|||
Note: including inplace operation of model_args.
|
||||
"""
|
||||
init_kwargs = _get_init_kwargs(model_args)
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_args.model_name_or_path,
|
||||
use_fast=model_args.use_fast_tokenizer,
|
||||
|
|
@ -43,6 +44,15 @@ def load_tokenizer(model_args: "ModelArguments") -> "PreTrainedTokenizer":
|
|||
padding_side="right",
|
||||
**init_kwargs,
|
||||
)
|
||||
except ValueError: # try the fast one
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_args.model_name_or_path,
|
||||
use_fast=True,
|
||||
split_special_tokens=model_args.split_special_tokens,
|
||||
padding_side="right",
|
||||
**init_kwargs,
|
||||
)
|
||||
|
||||
patch_tokenizer(tokenizer)
|
||||
return tokenizer
|
||||
|
||||
|
|
|
|||
|
|
@ -133,7 +133,9 @@ def _configure_quantization(
|
|||
if is_deepspeed_zero3_enabled():
|
||||
raise ValueError("DeepSpeed ZeRO-3 is incompatible with quantized models.")
|
||||
|
||||
if model_args.quantization_device_map != "auto":
|
||||
init_kwargs["device_map"] = {"": get_current_device()}
|
||||
|
||||
quantization_config: Dict[str, Any] = getattr(config, "quantization_config", None)
|
||||
quant_method = quantization_config.get("quant_method", "")
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue