README.md

metadata

pipeline_tag: text-generation
inference:
  parameters:
    temperature: 0.2
    top_p: 0.95
widget:
  - text: 'def print_hello_world():'
    example_title: Hello world
    group: Python
datasets:
  - bigcode/the-stack-v2-train
license: bigcode-openrail-m
library_name: transformers
tags:
  - code
  - mlx
base_model: bigcode/starcoder2-15b
model-index:
  - name: starcoder2-15b
    results:
      - task:
          type: text-generation
        dataset:
          name: CruxEval-I
          type: cruxeval-i
        metrics:
          - type: pass@1
            value: 48.1
      - task:
          type: text-generation
        dataset:
          name: DS-1000
          type: ds-1000
        metrics:
          - type: pass@1
            value: 33.8
      - task:
          type: text-generation
        dataset:
          name: GSM8K (PAL)
          type: gsm8k-pal
        metrics:
          - type: accuracy
            value: 65.1
      - task:
          type: text-generation
        dataset:
          name: HumanEval+
          type: humanevalplus
        metrics:
          - type: pass@1
            value: 37.8
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: humaneval
        metrics:
          - type: pass@1
            value: 46.3
      - task:
          type: text-generation
        dataset:
          name: RepoBench-v1.1
          type: repobench-v1.1
        metrics:
          - type: edit-smiliarity
            value: 74.08

mlx-community/bigcode-starcoder2-15b-6bit

The Model mlx-community/bigcode-starcoder2-15b-6bit was converted to MLX format from bigcode/starcoder2-15b using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/bigcode-starcoder2-15b-6bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)