Skip to content

Commit

Permalink
DOC: update builtin models (#365)
Browse files Browse the repository at this point in the history
  • Loading branch information
@UranusSeven
UranusSeven authored Aug 17, 2023
1 parent 5b53b52 commit 34ba817
Show file tree
Hide file tree
Showing 3 changed files with 78 additions and 61 deletions.
46 changes: 26 additions & 20 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -193,26 +193,32 @@ To view the builtin models, run the following command:
$ xinference list --all
```

| Name | Language | Ability |
|------------------|--------------|-----------------------|
| baichuan | ['en', 'zh'] | ['embed', 'generate'] |
| baichuan-chat | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2 | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2-32k | ['en', 'zh'] | ['embed', 'chat'] |
| falcon | ['en'] | ['embed', 'generate'] |
| falcon-instruct | ['en'] | ['embed', 'chat'] |
| gpt-2 | ['en'] | ['generate'] |
| llama-2 | ['en'] | ['embed', 'generate'] |
| llama-2-chat | ['en'] | ['embed', 'chat'] |
| opt | ['en'] | ['embed', 'generate'] |
| orca | ['en'] | ['embed', 'chat'] |
| qwen-chat | ['en', 'zh'] | ['embed', 'chat'] |
| starcoder | ['en'] | ['generate'] |
| starcoderplus | ['en'] | ['embed', 'generate'] |
| starchat-beta | ['en'] | ['embed', 'chat'] |
| vicuna-v1.3 | ['en'] | ['embed', 'chat'] |
| wizardlm-v1.0 | ['en'] | ['embed', 'chat'] |
| Name | Language | Ability |
|------------------|---------------|------------------------|
| baichuan | ['en', 'zh'] | ['embed', 'generate'] |
| baichuan-chat | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2 | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2-32k | ['en', 'zh'] | ['embed', 'chat'] |
| falcon | ['en'] | ['embed', 'generate'] |
| falcon-instruct | ['en'] | ['embed', 'chat'] |
| gpt-2 | ['en'] | ['generate'] |
| internlm | ['en', 'zh'] | ['embed', 'generate'] |
| internlm-chat | ['en', 'zh'] | ['embed', 'chat'] |
| internlm-chat-8k | ['en', 'zh'] | ['embed', 'chat'] |
| llama-2 | ['en'] | ['embed', 'generate'] |
| llama-2-chat | ['en'] | ['embed', 'chat'] |
| opt | ['en'] | ['embed', 'generate'] |
| orca | ['en'] | ['embed', 'chat'] |
| qwen-chat | ['en', 'zh'] | ['embed', 'chat'] |
| starchat-beta | ['en'] | ['embed', 'chat'] |
| starcoder | ['en'] | ['generate'] |
| starcoderplus | ['en'] | ['embed', 'generate'] |
| vicuna-v1.3 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5-16k | ['en'] | ['embed', 'chat'] |
| wizardlm-v1.0 | ['en'] | ['embed', 'chat'] |
| wizardmath-v1.0 | ['en'] | ['embed', 'chat'] |

For in-depth details on the built-in models, please refer to [built-in models](https://inference.readthedocs.io/en/latest/models/builtin/index.html).

Expand Down
47 changes: 26 additions & 21 deletions README_ja_JP.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -171,28 +171,33 @@ model.chat(
$ xinference list --all
```

### ggmlv3 モデル

| Name | Type | Language | Format | Size (in billions) | Quantization |
|---------------|------------------|----------|---------|--------------------|-----------------------------------------|
| llama-2 | Foundation Model | en | ggmlv3 | 7, 13 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| baichuan | Foundation Model | en, zh | ggmlv3 | 7 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| llama-2-chat | RLHF Model | en | ggmlv3 | 7, 13, 70 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| chatglm | SFT Model | en, zh | ggmlv3 | 6 | 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'q8_0' |
| chatglm2 | SFT Model | en, zh | ggmlv3 | 6 | 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'q8_0' |
| wizardlm-v1.0 | SFT Model | en | ggmlv3 | 7, 13, 33 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| wizardlm-v1.1 | SFT Model | en | ggmlv3 | 13 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| vicuna-v1.3 | SFT Model | en | ggmlv3 | 7, 13 | 'q2_K', 'q3_K_L', ... , 'q6_K', 'q8_0' |
| orca | SFT Model | en | ggmlv3 | 3, 7, 13 | 'q4_0', 'q4_1', 'q5_0', 'q5_1', 'q8_0' |

### pytorch モデル

| Name | Type | Language | Format | Size (in billions) | Quantization |
|---------------|------------------|----------|---------|--------------------|--------------------------|
| baichuan | Foundation Model | en, zh | pytorch | 7, 13 | '4-bit', '8-bit', 'none' |
| baichuan-chat | SFT Model | en, zh | pytorch | 13 | '4-bit', '8-bit', 'none' |
| vicuna-v1.3 | SFT Model | en | pytorch | 7, 13, 33 | '4-bit', '8-bit', 'none' |

| Name | Language | Ability |
|------------------|---------------|------------------------|
| baichuan | ['en', 'zh'] | ['embed', 'generate'] |
| baichuan-chat | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2 | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2-32k | ['en', 'zh'] | ['embed', 'chat'] |
| falcon | ['en'] | ['embed', 'generate'] |
| falcon-instruct | ['en'] | ['embed', 'chat'] |
| gpt-2 | ['en'] | ['generate'] |
| internlm | ['en', 'zh'] | ['embed', 'generate'] |
| internlm-chat | ['en', 'zh'] | ['embed', 'chat'] |
| internlm-chat-8k | ['en', 'zh'] | ['embed', 'chat'] |
| llama-2 | ['en'] | ['embed', 'generate'] |
| llama-2-chat | ['en'] | ['embed', 'chat'] |
| opt | ['en'] | ['embed', 'generate'] |
| orca | ['en'] | ['embed', 'chat'] |
| qwen-chat | ['en', 'zh'] | ['embed', 'chat'] |
| starchat-beta | ['en'] | ['embed', 'chat'] |
| starcoder | ['en'] | ['generate'] |
| starcoderplus | ['en'] | ['embed', 'generate'] |
| vicuna-v1.3 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5-16k | ['en'] | ['embed', 'chat'] |
| wizardlm-v1.0 | ['en'] | ['embed', 'chat'] |
| wizardmath-v1.0 | ['en'] | ['embed', 'chat'] |

**注**:
- Xinference は自動的にモデルをダウンロードし、デフォルトでは `${USER}/.xinference/cache` の下に保存されます。
Expand Down
46 changes: 26 additions & 20 deletions README_zh_CN.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -174,26 +174,32 @@ model.chat(
$ xinference list --all
```

| Name | Language | Ability |
|------------------|--------------|-----------------------|
| baichuan | ['en', 'zh'] | ['embed', 'generate'] |
| baichuan-chat | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2 | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2-32k | ['en', 'zh'] | ['embed', 'chat'] |
| falcon | ['en'] | ['embed', 'generate'] |
| falcon-instruct | ['en'] | ['embed', 'chat'] |
| gpt-2 | ['en'] | ['generate'] |
| llama-2 | ['en'] | ['embed', 'generate'] |
| llama-2-chat | ['en'] | ['embed', 'chat'] |
| opt | ['en'] | ['embed', 'generate'] |
| orca | ['en'] | ['embed', 'chat'] |
| qwen-chat | ['en', 'zh'] | ['embed', 'chat'] |
| starcoder | ['en'] | ['generate'] |
| starcoderplus | ['en'] | ['embed', 'generate'] |
| starchat-beta | ['en'] | ['embed', 'chat'] |
| vicuna-v1.3 | ['en'] | ['embed', 'chat'] |
| wizardlm-v1.0 | ['en'] | ['embed', 'chat'] |
| Name | Language | Ability |
|------------------|---------------|------------------------|
| baichuan | ['en', 'zh'] | ['embed', 'generate'] |
| baichuan-chat | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2 | ['en', 'zh'] | ['embed', 'chat'] |
| chatglm2-32k | ['en', 'zh'] | ['embed', 'chat'] |
| falcon | ['en'] | ['embed', 'generate'] |
| falcon-instruct | ['en'] | ['embed', 'chat'] |
| gpt-2 | ['en'] | ['generate'] |
| internlm | ['en', 'zh'] | ['embed', 'generate'] |
| internlm-chat | ['en', 'zh'] | ['embed', 'chat'] |
| internlm-chat-8k | ['en', 'zh'] | ['embed', 'chat'] |
| llama-2 | ['en'] | ['embed', 'generate'] |
| llama-2-chat | ['en'] | ['embed', 'chat'] |
| opt | ['en'] | ['embed', 'generate'] |
| orca | ['en'] | ['embed', 'chat'] |
| qwen-chat | ['en', 'zh'] | ['embed', 'chat'] |
| starchat-beta | ['en'] | ['embed', 'chat'] |
| starcoder | ['en'] | ['generate'] |
| starcoderplus | ['en'] | ['embed', 'generate'] |
| vicuna-v1.3 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5 | ['en'] | ['embed', 'chat'] |
| vicuna-v1.5-16k | ['en'] | ['embed', 'chat'] |
| wizardlm-v1.0 | ['en'] | ['embed', 'chat'] |
| wizardmath-v1.0 | ['en'] | ['embed', 'chat'] |

更多信息请参考 [内置模型](https://inference.readthedocs.io/en/latest/models/builtin/index.html)。

Expand Down

0 comments on commit 34ba817

Please sign in to comment.