README.md

metadata

license: other
language:
  - en
tags:
  - causal-lm
  - code
metrics:
  - code_eval
library_name: transformers
model-index:
  - name: stabilityai/stable-code-instruct-3b
    results:
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Python)
        metrics:
          - name: pass@1
            type: pass@1
            value: 32.4
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (C++)
        metrics:
          - name: pass@1
            type: pass@1
            value: 30.9
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Java)
        metrics:
          - name: pass@1
            type: pass@1
            value: 32.1
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (JavaScript)
        metrics:
          - name: pass@1
            type: pass@1
            value: 32.1
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (PHP)
        metrics:
          - name: pass@1
            type: pass@1
            value: 24.2
            verified: false
      - task:
          type: text-generation
        dataset:
          type: nuprl/MultiPL-E
          name: MultiPL-HumanEval (Rust)
        metrics:
          - name: pass@1
            type: pass@1
            value: 23
            verified: false

stable-code-instruct-3b

Model Description

stable-code-instruct-3b is a 2.7B billion parameter decoder-only language model tuned from stable-code-3b. This model was trained on a mix of publicly available datasets, synthetic datasets using Direct Preference Optimization (DPO).

This instruct tune demonstrates state-of-the-art performance (compared to models of similar size) on the MultiPL-E metrics across multiple programming languages tested using BigCode's Evaluation Harness, and on the code portions of MT Bench

Usage

Here's how you can run the model use the model:

# pip install -U transformers
# pip install accelerate

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stable-code-instruct-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("stabilityai/stable-code-instruct-3b", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.eval()
model = model.cuda()

messages = [
    {
        "role": "system",
        "content": "You are a helpful and polite assistant",
    },
    {
        "role": "user",
        "content": "Write a simple website in HTML. When a user clicks the button, it shows a random joke from a list of 4 jokes."
    },
]

prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

tokens = model.generate(
    **inputs,
    max_new_tokens=1024,
    temperature=0.5,
    top_p=0.95,
    top_k=100,
    do_sample=True,
    use_cache=True
)

output = tokenizer.batch_decode(tokens[:, inputs.input_ids.shape[-1]:], skip_special_tokens=False)[0]

How to Cite

@misc{stable-code-instruct-3b,
      url={[https://huggingface.co/stabilityai/stable-code-3b](https://huggingface.co/stabilityai/stable-code-instruct-3b)},
      title={Stable Code 3B},
      author={Phung, Duy, and Pinnaparaju, Nikhil and Adithyan, Reshinth and Tow, Jonathan and Cooper, Nathan}
}