mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-23 06:12:50 +08:00
Merge pull request #5910 from Cuiyn/index
Support Index series models. Former-commit-id: c58cc22d06eb1a466ad92601ceb74c9bae6abb51
This commit is contained in:
hoshi-hiyouga
GitHub
commit
6f79974e8b
@ -181,6 +181,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
|
||||
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
||||
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
||||
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |
|
||||
| [Index](https://huggingface.co/IndexTeam) | 1.9B | index |
|
||||
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
|
||||
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
|
||||
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
|
||||
@ -724,7 +725,7 @@ 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: [Baichuan 2](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) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](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) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
Please follow the model licenses to use the corresponding model weights: [Baichuan 2](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) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](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) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
|
||||
## Citation
|
||||
|
||||
|
||||
@ -182,6 +182,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
|
||||
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
||||
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
||||
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |
|
||||
| [Index](https://huggingface.co/IndexTeam) | 1.9B | index |
|
||||
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
|
||||
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
|
||||
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
|
||||
@ -724,7 +725,7 @@ run_name: test_run # 可选
|
||||
|
||||
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：[Baichuan 2](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) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](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) / [Yi-1.5](LICENSE) / [Yuan 2](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：[Baichuan 2](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) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](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) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
|
||||
|
||||
## 引用
|
||||
|
||||
|
||||
@ -691,6 +691,14 @@ _register_template(
|
||||
)
|
||||
|
||||
|
||||
_register_template(
|
||||
name="index",
|
||||
format_user=StringFormatter(slots=["reserved_0{{content}}reserved_1"]),
|
||||
format_system=StringFormatter(slots=["<unk>{{content}}"]),
|
||||
efficient_eos=True,
|
||||
)
|
||||
|
||||
|
||||
_register_template(
|
||||
name="intern",
|
||||
format_user=StringFormatter(slots=["<|User|>:{{content}}\n<|Bot|>:"]),
|
||||
|
||||
@ -596,6 +596,33 @@ register_model_group(
|
||||
)
|
||||
|
||||
|
||||
register_model_group(
|
||||
models={
|
||||
"Index-1.9B-Chat": {
|
||||
DownloadSource.DEFAULT: "IndexTeam/Index-1.9B-Chat",
|
||||
DownloadSource.MODELSCOPE: "IndexTeam/Index-1.9B-Chat",
|
||||
},
|
||||
"Index-1.9B-Character-Chat": {
|
||||
DownloadSource.DEFAULT: "IndexTeam/Index-1.9B-Character",
|
||||
DownloadSource.MODELSCOPE: "IndexTeam/Index-1.9B-Character",
|
||||
},
|
||||
"Index-1.9B-Base": {
|
||||
DownloadSource.DEFAULT: "IndexTeam/Index-1.9B",
|
||||
DownloadSource.MODELSCOPE: "IndexTeam/Index-1.9B",
|
||||
},
|
||||
"Index-1.9B-Base-Pure": {
|
||||
DownloadSource.DEFAULT: "IndexTeam/Index-1.9B-Pure",
|
||||
DownloadSource.MODELSCOPE: "IndexTeam/Index-1.9B-Pure",
|
||||
},
|
||||
"Index-1.9B-Chat-32K": {
|
||||
DownloadSource.DEFAULT: "IndexTeam/Index-1.9B-32K",
|
||||
DownloadSource.MODELSCOPE: "IndexTeam/Index-1.9B-32K",
|
||||
},
|
||||
},
|
||||
template="index",
|
||||
)
|
||||
|
||||
|
||||
register_model_group(
|
||||
models={
|
||||
"InternLM-7B": {
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user