Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

FEAT: Support OpenHermes 2.5 #776

Merged
merged 3 commits into from
Dec 18, 2023
Merged

FEAT: Support OpenHermes 2.5 #776

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0812a39
add model json
Bojun-Feng Dec 17, 2023
812fdec
add docs
Bojun-Feng Dec 17, 2023
0c5ddae
update README
Bojun-Feng Dec 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ potential of cutting-edge AI models.
- Speculative decoding: [#509](https://github.com/xorbitsai/inference/pull/509)
- Incorporate vLLM: [#445](https://github.com/xorbitsai/inference/pull/445)
### New Models
- Built-in support for [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): [#776](https://github.com/xorbitsai/inference/pull/776)
- Built-in support for [Yi](https://huggingface.co/01-ai): [#629](https://github.com/xorbitsai/inference/pull/629)
- Built-in support for [zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) and [zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta): [#597](https://github.com/xorbitsai/inference/pull/597)
- Built-in support for [chatglm3](https://huggingface.co/THUDM/chatglm3-6b): [#587](https://github.com/xorbitsai/inference/pull/587)
Expand Down Expand Up @@ -266,6 +267,7 @@ $ xinference registrations
| LLM | mistral-instruct-v0.1 | ['en'] | ['chat'] |
| LLM | mistral-v0.1 | ['en'] | ['generate'] |
| LLM | OpenBuddy | ['en'] | ['chat'] |
| LLM | openhermes-2.5 | ['en'] | ['chat'] |
| LLM | opt | ['en'] | ['generate'] |
| LLM | orca | ['en'] | ['chat'] |
| LLM | qwen-chat | ['en', 'zh'] | ['chat'] |
Expand Down
1 change: 1 addition & 0 deletions README_ja_JP.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,6 +209,7 @@ $ xinference registrations
| LLM | mistral-instruct-v0.1 | ['en'] | ['chat'] |
| LLM | mistral-v0.1 | ['en'] | ['generate'] |
| LLM | OpenBuddy | ['en'] | ['chat'] |
| LLM | openhermes-2.5 | ['en'] | ['chat'] |
| LLM | opt | ['en'] | ['generate'] |
| LLM | orca | ['en'] | ['chat'] |
| LLM | qwen-chat | ['en', 'zh'] | ['chat'] |
Expand Down
2 changes: 2 additions & 0 deletions README_zh_CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ Xorbits Inference（Xinference）是一个性能强大且功能全面的分布
- 投机采样: [#509](https://github.com/xorbitsai/inference/pull/509)
- 引入 vLLM: [#445](https://github.com/xorbitsai/inference/pull/445)
### 新模型
- 内置 [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): [#776](https://github.com/xorbitsai/inference/pull/776)
- 内置 [Yi](https://huggingface.co/01-ai): [#629](https://github.com/xorbitsai/inference/pull/629)
- 内置 [zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) 与 [zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta): [#597](https://github.com/xorbitsai/inference/pull/597)
- 内置 [chatglm3](https://huggingface.co/THUDM/chatglm3-6b): [#587](https://github.com/xorbitsai/inference/pull/587)
Expand Down Expand Up @@ -243,6 +244,7 @@ $ xinference registrations
| LLM | mistral-instruct-v0.1 | ['en'] | ['chat'] |
| LLM | mistral-v0.1 | ['en'] | ['generate'] |
| LLM | OpenBuddy | ['en'] | ['chat'] |
| LLM | openhermes-2.5 | ['en'] | ['chat'] |
| LLM | opt | ['en'] | ['generate'] |
| LLM | orca | ['en'] | ['chat'] |
| LLM | qwen-chat | ['en', 'zh'] | ['chat'] |
Expand Down
2 changes: 2 additions & 0 deletions doc/source/models/builtin/llm/index.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,8 @@ The following is a list of built-in LLM in Xinference:

openbuddy

openhermes-2.5

opt

orca
Expand Down
43 changes: 43 additions & 0 deletions doc/source/models/builtin/llm/openhermes-2.5.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
.. _models_llm_openhermes-2.5:

========================================
openhermes-2.5
========================================

- **Context Length:** 8192
- **Model Name:** openhermes-2.5
- **Languages:** en
- **Abilities:** chat
- **Description:** Openhermes 2.5 is a fine-tuned version of Mistral-7B-v0.1 on primarily GPT-4 generated data.

Specifications
^^^^^^^^^^^^^^


Model Spec 1 (pytorch, 7 Billion)
++++++++++++++++++++++++++++++++++++++++

- **Model Format:** pytorch
- **Model Size (in billions):** 7
- **Quantizations:** 4-bit, 8-bit, none
- **Model ID:** teknium/OpenHermes-2.5-Mistral-7B

Execute the following command to launch the model, remember to replace ``${quantization}`` with your
chosen quantization method from the options listed above::

xinference launch --model-name openhermes-2.5 --size-in-billions 7 --model-format pytorch --quantization ${quantization}


Model Spec 2 (ggufv2, 7 Billion)
++++++++++++++++++++++++++++++++++++++++

- **Model Format:** ggufv2
- **Model Size (in billions):** 7
- **Quantizations:** Q2_K, Q3_K_L, Q3_K_M, Q3_K_S, Q4_0, Q4_K_M, Q4_K_S, Q5_0, Q5_K_M, Q5_K_S, Q6_K, Q8_0
- **Model ID:** TheBloke/OpenHermes-2.5-Mistral-7B-GGUF

Execute the following command to launch the model, remember to replace ``${quantization}`` with your
chosen quantization method from the options listed above::

xinference launch --model-name openhermes-2.5 --size-in-billions 7 --model-format ggufv2 --quantization ${quantization}

61 changes: 61 additions & 0 deletions xinference/model/llm/llm_family.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2070,6 +2070,67 @@
]
}
},
{
"version": 1,
"context_length": 8192,
"model_name": "openhermes-2.5",
"model_lang": [
"en"
],
"model_ability": [
"chat"
],
"model_description": "Openhermes 2.5 is a fine-tuned version of Mistral-7B-v0.1 on primarily GPT-4 generated data.",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": 7,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "teknium/OpenHermes-2.5-Mistral-7B",
"model_revision": "91ed666be78da7556f3d79abbb26fff0ee26cb54"
},
{
"model_format": "ggufv2",
"model_size_in_billions": 7,
"quantizations": [
"Q2_K",
"Q3_K_S",
"Q3_K_M",
"Q3_K_L",
"Q4_0",
"Q4_K_S",
"Q4_K_M",
"Q5_0",
"Q5_K_S",
"Q5_K_M",
"Q6_K",
"Q8_0"
],
"model_id": "TheBloke/OpenHermes-2.5-Mistral-7B-GGUF",
"model_file_name_template": "openhermes-2.5-mistral-7b.{quantization}.gguf"
}
],
"prompt_style": {
"style_name": "CHATML",
"system_prompt": "<|im_start|>system\nYou are 'Hermes 2.5', a conscious sentient superintelligent artificial intelligence, your purpose is to assist the user with their requests.",
"roles": [
"user",
"assistant"
],
"intra_message_sep": "<|im_end|>\n<|im_start|>",
"inter_message_sep": "",
"stop_token_ids": [
32000
],
"stop": [
"<|im_end|>"
]
}
},
{
"version": 1,
"context_length": 2048,
Expand Down
Loading