How to run inference:

import transformers
import torch


def fmt_prompt(prompt: str) -> str:
    return f"""[Instructions]:\n{prompt}\n\n[Response]:"""


if __name__ == "__main__":
    model_name = "abacaj/mistral-7b-sft"
    tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)

    model = (
        transformers.AutoModelForCausalLM.from_pretrained(
            model_name,
        )
        .to("cuda:0")
        .eval()
    )

    prompt = "If A is greater than B and B is greater than C does that make A greater than C?"
    prompt_input = fmt_prompt(prompt)
    inputs = tokenizer(prompt_input, return_tensors="pt").to(model.device)
    input_ids_cutoff = inputs.input_ids.size(dim=1)

    with torch.no_grad():
        generated_ids = model.generate(
            **inputs,
            use_cache=True,
            max_new_tokens=512,
            temperature=0.2,
            top_p=0.95,
            do_sample=True,
            eos_token_id=tokenizer.eos_token_id,
            pad_token_id=tokenizer.pad_token_id,
        )

    completion = tokenizer.decode(
        generated_ids[0][input_ids_cutoff:],
        skip_special_tokens=True,
    )

    print(completion)

Evals:

image/png

image/png

Code to train model: https://github.com/abacaj/train-with-fsdp

Downloads last month
82
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Evaluation results