add codegemma
This commit is contained in:
hiyouga
parent
e0dbac2845
commit
6543f3d449
|
|
@ -132,10 +132,10 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
|
|||
| [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 |
|
||||
| [Command-R](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 |
|
||||
| [Gemma/CodeGemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma |
|
||||
| [InternLM2](https://huggingface.co/internlm) | 7B/20B | wqkv | intern2 |
|
||||
| [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - |
|
||||
| [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 |
|
||||
|
|
@ -428,7 +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) / [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)
|
||||
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) / [Command-R](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
|
||||
|
||||
|
|
|
|||
|
|
@ -132,10 +132,10 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
|
|||
| [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 |
|
||||
| [Command-R](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 |
|
||||
| [Gemma/CodeGemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma |
|
||||
| [InternLM2](https://huggingface.co/internlm) | 7B/20B | wqkv | intern2 |
|
||||
| [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - |
|
||||
| [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 |
|
||||
|
|
@ -428,7 +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) / [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)
|
||||
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) / [Command-R](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
|
||||
|
||||
|
|
|
|||
|
|
@ -385,6 +385,23 @@ register_model_group(
|
|||
)
|
||||
|
||||
|
||||
register_model_group(
|
||||
models={
|
||||
"CodeGemma-2B": {
|
||||
DownloadSource.DEFAULT: "google/codegemma-2b",
|
||||
},
|
||||
"CodeGemma-7B": {
|
||||
DownloadSource.DEFAULT: "google/codegemma-7b",
|
||||
},
|
||||
"CodeGemma-7B-Chat": {
|
||||
DownloadSource.DEFAULT: "google/codegemma-7b-it",
|
||||
DownloadSource.MODELSCOPE: "AI-ModelScope/codegemma-7b-it",
|
||||
},
|
||||
},
|
||||
template="gemma",
|
||||
)
|
||||
|
||||
|
||||
register_model_group(
|
||||
models={
|
||||
"InternLM-7B": {
|
||||
|
|
|
|||
|
|
@ -48,7 +48,6 @@ def load_tokenizer(model_args: "ModelArguments") -> "PreTrainedTokenizer":
|
|||
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,
|
||||
)
|
||||
|
|
|
|||
Loading…
Reference in New Issue