metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
datasets:
- abacusai/MetaMathFewshot
- shahules786/orca-chat
- anon8231489123/ShareGPT_Vicuna_unfiltered
This model was trained on our MetamathFewshot (https://huggingface.co/datasets/abacusai/MetaMathFewshot) dataset, as well as the Vicuna (https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset and the OrcaChat (https://huggingface.co/datasets/shahules786/orca-chat) dataset.
It has been finetuned from base Mistral 7B (https://huggingface.co/mistralai/Mistral-7B-v0.1)
Usage
This model uses a specific prompt format which is encoded as a chat template. To apply this, you can use the tokenizer.apply_chat_template() method of the attached tokenizer:
messages = [
{"role": "user", "content": "What is the capital of Spain?"},
{"role": "assistant", "content": "The capital of Spain is Madrid."}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
Evaluation Results
HuggingFace Leaderboard
Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
---|---|---|---|---|---|---|
67.33 | 59.64 | 81.82 | 61.69 | 53.23 | 78.45 | 69.14 |
For comparison the GSM8K score for the original metamath/MetaMath-Mistral-7B
was 68.84 and average score was 65.78.
MT-Bench
Turn 1 | Turn 2 | Average |
---|---|---|
6.90 | 6.52 | 6.71 |
Training Details
Instruction tuned with the following parameters:
- LORA, Rank 8, Alpha 16, Dropout 0.05, all modules (QKV and MLP)
- 3 epochs
- Micro Batch Size 32 over 4xH100, gradient accumulation steps = 1
- AdamW with learning rate 5e-5