metadata

language:
  - en
metrics:
  - code_eval
base_model:
  - deepseek-ai/deepseek-coder-6.7b-base
pipeline_tag: text-generation
library_name: transformers
tags:
  - code

AssertSolver

Model Details

Model Description

Finetuned from model: deepseek-ai/deepseek-coder-6.7b-base

Model Sources

Paper: Insights from Rights and Wrongs: A Large Language Model for Solving Assertion Failures in RTL Design

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "1412312anonymous/AssertSolver"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
prompt = "Tell me how to fix the bugs inside: `always(*) // Pretend that this * should be rst`"

messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(
    inputs,
    max_new_tokens=512,
    do_sample=False,
    top_k=50,
    top_p=0.95,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(outputs[0][len(inputs[0]) :], skip_special_tokens=True))