README.md · tensorblock/starcoder2-3b-GGUF at main

metadata

pipeline_tag: text-generation
inference: true
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
  - TensorBlock
  - GGUF
base_model: bigcode/starcoder2-3b
model-index:
  - name: starcoder2-3b
    results:
      - task:
          type: text-generation
        dataset:
          name: CruxEval-I
          type: cruxeval-i
        metrics:
          - type: pass@1
            value: 32.7
      - task:
          type: text-generation
        dataset:
          name: DS-1000
          type: ds-1000
        metrics:
          - type: pass@1
            value: 25
      - task:
          type: text-generation
        dataset:
          name: GSM8K (PAL)
          type: gsm8k-pal
        metrics:
          - type: accuracy
            value: 27.7
      - task:
          type: text-generation
        dataset:
          name: HumanEval+
          type: humanevalplus
        metrics:
          - type: pass@1
            value: 27.4
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: humaneval
        metrics:
          - type: pass@1
            value: 31.7
      - task:
          type: text-generation
        dataset:
          name: RepoBench-v1.1
          type: repobench-v1.1
        metrics:
          - type: edit-smiliarity
            value: 71.19

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

bigcode/starcoder2-3b - GGUF

This repo contains GGUF format model files for bigcode/starcoder2-3b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
starcoder2-3b-Q2_K.gguf	Q2_K	1.139 GB	smallest, significant quality loss - not recommended for most purposes
starcoder2-3b-Q3_K_S.gguf	Q3_K_S	1.273 GB	very small, high quality loss
starcoder2-3b-Q3_K_M.gguf	Q3_K_M	1.455 GB	very small, high quality loss
starcoder2-3b-Q3_K_L.gguf	Q3_K_L	1.618 GB	small, substantial quality loss
starcoder2-3b-Q4_0.gguf	Q4_0	1.629 GB	legacy; small, very high quality loss - prefer using Q3_K_M
starcoder2-3b-Q4_K_S.gguf	Q4_K_S	1.642 GB	small, greater quality loss
starcoder2-3b-Q4_K_M.gguf	Q4_K_M	1.758 GB	medium, balanced quality - recommended
starcoder2-3b-Q5_0.gguf	Q5_0	1.964 GB	legacy; medium, balanced quality - prefer using Q4_K_M
starcoder2-3b-Q5_K_S.gguf	Q5_K_S	1.964 GB	large, low quality loss - recommended
starcoder2-3b-Q5_K_M.gguf	Q5_K_M	2.031 GB	large, very low quality loss - recommended
starcoder2-3b-Q6_K.gguf	Q6_K	2.320 GB	very large, extremely low quality loss
starcoder2-3b-Q8_0.gguf	Q8_0	3.003 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/starcoder2-3b-GGUF --include "starcoder2-3b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/starcoder2-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'