初始化项目，由ModelHub XC社区提供模型
Model: solidrust/Hermes-2-Pro-Mistral-7B-AWQ Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
168
README.md
Normal file
168
README.md
Normal file
@@ -0,0 +1,168 @@
|
||||
---
|
||||
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
|
||||
tags:
|
||||
- Mistral
|
||||
- instruct
|
||||
- finetune
|
||||
- chatml
|
||||
- DPO
|
||||
- RLHF
|
||||
- gpt4
|
||||
- synthetic data
|
||||
- distillation
|
||||
- function calling
|
||||
- json mode
|
||||
- quantized
|
||||
- 4-bit
|
||||
- AWQ
|
||||
- text-generation
|
||||
- autotrain_compatible
|
||||
- endpoints_compatible
|
||||
- chatml
|
||||
model-index:
|
||||
- name: Hermes-2-Pro-Mistral-7B
|
||||
results: []
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
datasets:
|
||||
- teknium/OpenHermes-2.5
|
||||
widget:
|
||||
- example_title: Hermes 2 Pro
|
||||
messages:
|
||||
- role: system
|
||||
content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
|
||||
- role: user
|
||||
content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.
|
||||
model_type: mistral
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
prompt_template: '<|im_start|>system
|
||||
|
||||
{system_message}<|im_end|>
|
||||
|
||||
<|im_start|>user
|
||||
|
||||
{prompt}<|im_end|>
|
||||
|
||||
<|im_start|>assistant
|
||||
|
||||
'
|
||||
quantized_by: Suparious
|
||||
---
|
||||
# NousResearch/Hermes-2-Pro-Mistral-7B AWQ
|
||||
|
||||
- Model creator: [NousResearch](https://huggingface.co/NousResearch)
|
||||
- Original model: [Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
|
||||
|
||||
|
||||
|
||||
## Model Summary
|
||||
|
||||
Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes!
|
||||
|
||||
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
|
||||
|
||||
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
|
||||
|
||||
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
|
||||
|
||||
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
|
||||
|
||||
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
|
||||
|
||||
## How to use
|
||||
|
||||
### Install the necessary packages
|
||||
|
||||
```bash
|
||||
pip install --upgrade autoawq autoawq-kernels
|
||||
```
|
||||
|
||||
### Example Python code
|
||||
|
||||
```python
|
||||
from awq import AutoAWQForCausalLM
|
||||
from transformers import AutoTokenizer, TextStreamer
|
||||
|
||||
model_path = "solidrust/Hermes-2-Pro-Mistral-7B-AWQ"
|
||||
system_message = "You are Hermes, incarnated as a powerful AI."
|
||||
|
||||
# Load model
|
||||
model = AutoAWQForCausalLM.from_quantized(model_path,
|
||||
fuse_layers=True)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||||
trust_remote_code=True)
|
||||
streamer = TextStreamer(tokenizer,
|
||||
skip_prompt=True,
|
||||
skip_special_tokens=True)
|
||||
|
||||
# Convert prompt to tokens
|
||||
prompt_template = """\
|
||||
<|im_start|>system
|
||||
{system_message}<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant"""
|
||||
|
||||
prompt = "You're standing on the surface of the Earth. "\
|
||||
"You walk one mile south, one mile west and one mile north. "\
|
||||
"You end up exactly where you started. Where are you?"
|
||||
|
||||
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
|
||||
return_tensors='pt').input_ids.cuda()
|
||||
|
||||
# Generate output
|
||||
generation_output = model.generate(tokens,
|
||||
streamer=streamer,
|
||||
max_new_tokens=512)
|
||||
|
||||
```
|
||||
|
||||
### About AWQ
|
||||
|
||||
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
|
||||
|
||||
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
|
||||
|
||||
It is supported by:
|
||||
|
||||
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
|
||||
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
|
||||
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
|
||||
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
|
||||
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
|
||||
|
||||
## Prompt template: ChatML
|
||||
|
||||
```plaintext
|
||||
<|im_start|>system
|
||||
{system_message}<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
## Function calling
|
||||
|
||||
System prompt example:
|
||||
|
||||
```plaintext
|
||||
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags.
|
||||
You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.
|
||||
Use the following json schema for each tool call you will make: {"title": "FunctionCall", "type": "object", "properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"]}
|
||||
For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
||||
<tool_call>
|
||||
{"arguments": <args-dict>, "name": <function-name>}
|
||||
</tool_call>
|
||||
```
|
||||
|
||||
## How to cite:
|
||||
|
||||
```plaintext
|
||||
@misc{Hermes-2-Pro-Mistral-7B,
|
||||
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B]https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)},
|
||||
title={Hermes-2-Pro-Mistral-7B},
|
||||
author={"interstellarninja", "Teknium", "theemozilla", "karan4d", "huemin_art"}
|
||||
}
|
||||
```
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_start|>": 32001
|
||||
}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "/srv/home/shaun/.cache/huggingface/hub/models--NousResearch--Hermes-2-Pro-Mistral-7B/snapshots/8dd571ec94aa1709b4b02a07e1201678b939ef44",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"modules_to_not_convert": null,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32032
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 32000,
|
||||
"transformers_version": "4.38.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:72a493cfda34a69a01df8e6239b9a07072693c55bae16db1fc05c6c50e371c96
|
||||
size 4151404520
|
||||
6
quant_config.json
Normal file
6
quant_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"zero_point": true,
|
||||
"q_group_size": 128,
|
||||
"w_bit": 4,
|
||||
"version": "GEMM"
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91140
tokenizer.json
Normal file
91140
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
61
tokenizer_config.json
Normal file
61
tokenizer_config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user