1. Model Details
Introducing xinchen9/Llama3.1_8B_Instruct_CoT, an advanced language model comprising 8 billion parameters. It has been fine-trained based on meta-llama/Meta-Llama-3.1-8B-Instruct.
The llama3-b8 model was fine-tuning on dataset CoT_Collection.
The training step is 46,000. The batch of each device is 8 and toal GPU is 5. Learning Rate: 0.0003
2. How to Use
Here give some examples of how to use our model.
Text Completion
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
model_name = "xinchen9/Llama3.1_8B_Instruct_CoT"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id
3 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.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 15.73 |
IFEval (0-Shot) | 30.03 |
BBH (3-Shot) | 22.06 |
MATH Lvl 5 (4-Shot) | 4.61 |
GPQA (0-shot) | 7.16 |
MuSR (0-shot) | 8.46 |
MMLU-PRO (5-shot) | 22.04 |
- Downloads last month
- 16
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard30.030
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard22.060
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard4.610
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.160
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.460
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard22.040