mistral-7b_open_platypus

mistral-7b_open_platypus

mistral-7b_open_platypus is an instruction fine-tuned model based on the Mistral-7B transformer architecture.

Benchmark Metrics

We use state-of-the-art Language Model Evaluation Harness to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.

Model Details

• Trained by: Luiz G A Alves
• Model type: mistral-7b_open_platypus is an auto-regressive language model based on the Mistral-7B transformer architecture.
• Language(s): English

How to use:

# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/mistral-7b_open_platypus")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])

or, you can load the model direclty using:

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lgaalves/mistral-7b_open_platypus")
model = AutoModelForCausalLM.from_pretrained("lgaalves/mistral-7b_open_platypus")

Prompt format

 "<s>[INST] What is your favourite condiment? [/INST]"

Training Dataset

lgaalves/mistral-7b_open_platypus trained using STEM and logic based dataset garage-bAInd/Open-Platypus.

Training Procedure

lgaalves/mistral-7b_open_platypus was instruction fine-tuned using LoRA on 1 Tesla V100-SXM2-16GB. In total, it took 11 hours to fine tune the model.

Limitations and bias

Mistral 7B and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here