初始化项目，由ModelHub XC社区提供模型
Model: Intel/neural-chat-7b-v3-2 Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
250
README.md
Normal file
250
README.md
Normal file
@@ -0,0 +1,250 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- LLMs
|
||||
- mistral
|
||||
- math
|
||||
- Intel
|
||||
model-index:
|
||||
- name: neural-chat-7b-v3-2
|
||||
results:
|
||||
- task:
|
||||
type: Large Language Model
|
||||
name: Large Language Model
|
||||
dataset:
|
||||
type: meta-math/MetaMathQA
|
||||
name: meta-math/MetaMathQA
|
||||
metrics:
|
||||
- type: ARC (25-shot)
|
||||
value: 67.49
|
||||
name: ARC (25-shot)
|
||||
verified: true
|
||||
- type: HellaSwag (10-shot)
|
||||
value: 83.92
|
||||
name: HellaSwag (10-shot)
|
||||
verified: true
|
||||
- type: MMLU (5-shot)
|
||||
value: 63.55
|
||||
name: MMLU (5-shot)
|
||||
verified: true
|
||||
- type: TruthfulQA (0-shot)
|
||||
value: 59.68
|
||||
name: TruthfulQA (0-shot)
|
||||
verified: true
|
||||
- type: Winogrande (5-shot)
|
||||
value: 79.95
|
||||
name: Winogrande (5-shot)
|
||||
verified: true
|
||||
- type: GSM8K (5-shot)
|
||||
value: 55.12
|
||||
name: GSM8K (5-shot)
|
||||
verified: true
|
||||
datasets:
|
||||
- meta-math/MetaMathQA
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
## Model Details: Neural-Chat-v3-2
|
||||
|
||||
This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1) on the [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA) dataset. The model was aligned using the Direct Performance Optimization (DPO) method with [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs). The [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1) was originally fine-tuned from [mistralai/Mistral-7B-v-0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). For more information, refer to the Medium article [The Practice of Supervised Fine-tuning and Direct Preference Optimization on Intel Gaudi2](https://medium.com/@NeuralCompressor/the-practice-of-supervised-finetuning-and-direct-preference-optimization-on-habana-gaudi2-a1197d8a3cd3).
|
||||
|
||||
<p align="center">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/6297f0e30bd2f58c647abb1d/ctASHUT5QYIxMsOFa-sHC.webp" width="500"/>
|
||||
Photo by Google DeepMind on Unsplash
|
||||
</p>
|
||||
|
||||
| Model Detail | Description |
|
||||
| ----------- | ----------- |
|
||||
| Model Authors - Company | Intel. The NeuralChat team with members from DCAI/AISE/AIPT. Core team members: Kaokao Lv, Liang Lv, Chang Wang, Wenxin Zhang, Xuhui Ren, and Haihao Shen.|
|
||||
| Date | December, 2023 |
|
||||
| Version | v3-2 |
|
||||
| Type | 7B Large Language Model |
|
||||
| Paper or Other Resources | [Medium Blog](https://medium.com/@NeuralCompressor/the-practice-of-supervised-finetuning-and-direct-preference-optimization-on-habana-gaudi2-a1197d8a3cd3) |
|
||||
| License | Apache 2.0 |
|
||||
| Questions or Comments | [Community Tab](https://huggingface.co/Intel/neural-chat-7b-v3-3/discussions) and [Intel Developers Discord](https://discord.gg/rv2Gp55UJQ)|
|
||||
|
||||
| Intended Use | Description |
|
||||
| ----------- | ----------- |
|
||||
| Primary intended uses | You can use the fine-tuned model for several language-related tasks. Checkout the [LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) to see how this model is doing. |
|
||||
| Primary intended users | Anyone doing inference on language-related tasks. |
|
||||
| Out-of-scope uses | This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.|
|
||||
|
||||
## How To Use
|
||||
|
||||
Context length for this model: 8192 tokens (same as [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1))
|
||||
|
||||
### Reproduce the model
|
||||
Here is the sample code to reproduce the model: [GitHub sample code](https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/neural_chat/examples/finetuning/finetune_neuralchat_v3). Here is the documentation to reproduce building the model:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/intel/intel-extension-for-transformers.git
|
||||
cd intel-extension-for-transformers
|
||||
|
||||
docker build --no-cache ./ --target hpu --build-arg REPO=https://github.com/intel/intel-extension-for-transformers.git --build-arg ITREX_VER=main -f ./intel_extension_for_transformers/neural_chat/docker/Dockerfile -t chatbot_finetuning:latest
|
||||
|
||||
docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host chatbot_finetuning:latest
|
||||
|
||||
# after entering docker container
|
||||
cd examples/finetuning/finetune_neuralchat_v3
|
||||
|
||||
```
|
||||
We select the latest pretrained mistralai/Mistral-7B-v0.1 and the open source dataset Open-Orca/SlimOrca to conduct the experiment.
|
||||
|
||||
The below script use deepspeed zero2 to lanuch the training with 8 cards Gaudi2. In the `finetune_neuralchat_v3.py`, the default `use_habana=True, use_lazy_mode=True, device="hpu"` for Gaudi2. And if you want to run it on NVIDIA GPU, you can set them `use_habana=False, use_lazy_mode=False, device="auto"`.
|
||||
|
||||
```python
|
||||
deepspeed --include localhost:0,1,2,3,4,5,6,7 \
|
||||
--master_port 29501 \
|
||||
finetune_neuralchat_v3.py
|
||||
```
|
||||
|
||||
Merge the LoRA weights:
|
||||
|
||||
```python
|
||||
python apply_lora.py \
|
||||
--base-model-path mistralai/Mistral-7B-v0.1 \
|
||||
--lora-model-path finetuned_model/ \
|
||||
--output-path finetuned_model_lora
|
||||
```
|
||||
|
||||
### Use the model
|
||||
|
||||
### FP32 Inference with Transformers
|
||||
|
||||
```python
|
||||
import transformers
|
||||
|
||||
|
||||
model_name = 'Intel/neural-chat-7b-v3-2'
|
||||
model = transformers.AutoModelForCausalLM.from_pretrained(model_name)
|
||||
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
def generate_response(system_input, user_input):
|
||||
|
||||
# Format the input using the provided template
|
||||
prompt = f"### System:\n{system_input}\n### User:\n{user_input}\n### Assistant:\n"
|
||||
|
||||
# Tokenize and encode the prompt
|
||||
inputs = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=False)
|
||||
|
||||
# Generate a response
|
||||
outputs = model.generate(inputs, max_length=1000, num_return_sequences=1)
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
|
||||
# Extract only the assistant's response
|
||||
return response.split("### Assistant:\n")[-1]
|
||||
|
||||
|
||||
# Example usage
|
||||
system_input = "You are a math expert assistant. Your mission is to help users understand and solve various math problems. You should provide step-by-step solutions, explain reasonings and give the correct answer."
|
||||
user_input = "calculate 100 + 520 + 60"
|
||||
response = generate_response(system_input, user_input)
|
||||
print(response)
|
||||
|
||||
# expected response
|
||||
"""
|
||||
To calculate the sum of 100, 520, and 60, we will follow these steps:
|
||||
|
||||
1. Add the first two numbers: 100 + 520
|
||||
2. Add the result from step 1 to the third number: (100 + 520) + 60
|
||||
|
||||
Step 1: Add 100 and 520
|
||||
100 + 520 = 620
|
||||
|
||||
Step 2: Add the result from step 1 to the third number (60)
|
||||
(620) + 60 = 680
|
||||
|
||||
So, the sum of 100, 520, and 60 is 680.
|
||||
"""
|
||||
```
|
||||
|
||||
### BF16 Inference with Intel Extension for Transformers and Intel Extension for Pytorch
|
||||
```python
|
||||
from transformers import AutoTokenizer, TextStreamer
|
||||
import torch
|
||||
from intel_extension_for_transformers.transformers import AutoModelForCausalLM
|
||||
import intel_extension_for_pytorch as ipex
|
||||
|
||||
model_name = "Intel/neural-chat-7b-v3-2"
|
||||
prompt = "Once upon a time, there existed a little girl,"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").input_ids
|
||||
streamer = TextStreamer(tokenizer)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
|
||||
model = ipex.optimize(model.eval(), dtype=torch.bfloat16, inplace=True, level="O1", auto_kernel_selection=True)
|
||||
|
||||
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300)
|
||||
```
|
||||
|
||||
### INT4 Inference with Transformers and Intel Extension for Transformers
|
||||
```python
|
||||
from transformers import AutoTokenizer, TextStreamer
|
||||
from intel_extension_for_transformers.transformers import AutoModelForCausalLM, WeightOnlyQuantConfig
|
||||
model_name = "Intel/neural-chat-7b-v3-2"
|
||||
|
||||
# for int8, should set weight_dtype="int8"
|
||||
config = WeightOnlyQuantConfig(compute_dtype="bf16", weight_dtype="int4")
|
||||
prompt = "Once upon a time, there existed a little girl,"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").input_ids
|
||||
streamer = TextStreamer(tokenizer)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=config)
|
||||
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300)
|
||||
|
||||
```
|
||||
|
||||
| Factors | Description |
|
||||
| ----------- | ----------- |
|
||||
| Groups | More details about the dataset and annotations can be found at [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA), the project page https://meta-math.github.io/, and the associated paper at https://arxiv.org/abs/2309.12284. |
|
||||
| Instrumentation | The performance of the model can vary depending on the inputs to the model. In this case, the prompts provided can drastically change the prediction of the language model. |
|
||||
| Environment | The model was trained on the Intel Gaudi 2 processor (8 cards). |
|
||||
| Card Prompts | Model deployment on alternate hardware and software will change model performance. The model evaluation factors are from the Hugging Face LLM leaderboard: ARC, HellaSwag, MMLU, TruthfulQA, Winogrande, and GSM8K (see Quantitative Analyses below). |
|
||||
|
||||
| Metrics | Description |
|
||||
| ----------- | ----------- |
|
||||
| Model performance measures | The model performance was evaluated against other LLMs according to the measures on the LLM leaderboard. These were selected as this has become the standard for LLM performance. |
|
||||
| Decision thresholds | No decision thresholds were used. |
|
||||
| Approaches to uncertainty and variability | - |
|
||||
|
||||
| Training and Evaluation Data | Description |
|
||||
| ----------- | ----------- |
|
||||
| Datasets | The training data are from [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA), which is augmented from the GSM8k and MATH training sets. There is no contamination from the GSM8k test set, as this was left out during training.|
|
||||
| Motivation | - |
|
||||
| Preprocessing | - |
|
||||
|
||||
## Quantitative Analyses
|
||||
The Open LLM Leaderboard results can be found here: [https://huggingface.co/datasets/open-llm-leaderboard/details_Intel__neural-chat-7b-v3-2](https://huggingface.co/datasets/open-llm-leaderboard/details_Intel__neural-chat-7b-v3-2). The metrics came out to:
|
||||
|
||||
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 68.29 |
|
||||
| ARC (25-shot) | 67.49 |
|
||||
| HellaSwag (10-shot) | 83.92 |
|
||||
| MMLU (5-shot) | 63.55 |
|
||||
| TruthfulQA (0-shot) | 59.68 |
|
||||
| Winogrande (5-shot) | 79.95 |
|
||||
| GSM8K (5-shot) | 55.12 |
|
||||
|
||||
## Ethical Considerations and Limitations
|
||||
Neural-chat-7b-v3-2 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||
|
||||
Therefore, before deploying any applications of neural-chat-7b-v3-2, developers should perform safety testing.
|
||||
|
||||
## Caveats and Recommendations
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
||||
|
||||
Here are a couple of useful links to learn more about Intel's AI software:
|
||||
* Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
|
||||
* Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
|
||||
|
||||
## Disclaimer
|
||||
|
||||
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"</s>": 2,
|
||||
"<s>": 1,
|
||||
"<unk>": 0
|
||||
}
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "/models/habana_orca_math/habana-mistral-7b-finetuned-orca-math-4800",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"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,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.34.0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f4783521b240662e1ebe099e25ca592da903e22b9f408f966be81df91d7582e4
|
||||
size 9943028044
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:80562761b9ed7e05376d86c14b85b0ed83700634a64c542f7633d8af4bfcc05d
|
||||
size 4540535647
|
||||
3
pytorch_model.bin.index.json
Normal file
3
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f2d239108d89fb1568b9041e23f8526879c3fd500f65ac8d7c3204b270b648ef
|
||||
size 23950
|
||||
10
special_tokens_map.json
Normal file
10
special_tokens_map.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc
|
||||
size 1795303
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
44
tokenizer_config.json
Normal file
44
tokenizer_config.json
Normal file
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user