license: apache-2.0
Fine-tuning on Habana Gaudi2
This model is a fine-tuned model based on mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca. Then we align it with DPO algorithm. For more details, you can refer our blog: The Practice of Supervised Fine-tuning and Direct Preference Optimization on Habana Gaudi2.
Model date
Neural-chat-7b-v3 was trained between September and October, 2023.
Evaluation
We submit our model to open_llm_leaderboard, and the model performance has been improved significantly as we see from the average metric of 7 tasks from the leaderboard.
| Model | Average ⬆️ | ARC (25-s) ⬆️ | HellaSwag (10-s) ⬆️ | MMLU (5-s) ⬆️ | TruthfulQA (MC) (0-s) ⬆️ | Winogrande (5-s) | GSM8K (5-s) | DROP (3-s) |
|---|---|---|---|---|---|---|---|---|
| mistralai/Mistral-7B-v0.1 | 50.32 | 59.58 | 83.31 | 64.16 | 42.15 | 78.37 | 18.12 | 6.14 |
| Ours | 57.31 | 67.15 | 83.29 | 62.26 | 58.77 | 78.06 | 1.21 | 50.43 |
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-04
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-HPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size:
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2.0
Prompt Template
### System:
{system}
### User:
{usr}
### Assistant:
FP32 Inference with transformers
from transformers import AutoTokenizer, TextStreamer
model_name = "Intel/neural-chat-7b-v3"
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)
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300)
)
INT4 Inference with transformers
from transformers import AutoTokenizer, TextStreamer
from intel_extension_for_transformers.transformers import AutoModelForCausalLM, WeightOnlyQuantConfig
model_name = "Intel/neural-chat-7b-v3"
config = WeightOnlyQuantConfig(compute_dtype="int8", 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)
)
Ethical Considerations and Limitations
neural-chat-7b-v3 can produce factually incorrect output, and should not be relied on to produce factually accurate information. neural-chat-7b-v3 was trained on Open-Orca/SlimOrca based on mistralai/Mistral-7B-v0.1. 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, developers should perform safety testing.
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.
Organizations developing the model
The NeuralChat team with members from Intel/DCAI/AISE. Core team members: Kaokao Lv, Liang Lv, Chang Wang, Wenxin Zhang, Xuhui Ren, and Haihao Shen.
Useful links
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 57.31 |
| ARC (25-shot) | 67.15 |
| HellaSwag (10-shot) | 83.29 |
| MMLU (5-shot) | 62.26 |
| TruthfulQA (0-shot) | 58.77 |
| Winogrande (5-shot) | 78.06 |
| GSM8K (5-shot) | 1.21 |
| DROP (3-shot) | 50.43 |