README.md

metadata

license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
datasets:
  - OpenCoder-LLM/opc-sft-stage1
  - OpenCoder-LLM/opc-sft-stage2
  - microsoft/orca-agentinstruct-1M-v1
  - microsoft/orca-math-word-problems-200k
  - NousResearch/hermes-function-calling-v1
  - AI-MO/NuminaMath-CoT
  - AI-MO/NuminaMath-TIR
  - allenai/tulu-3-sft-mixture
  - cognitivecomputations/dolphin-coder
  - HuggingFaceTB/smoltalk
  - cognitivecomputations/samantha-data
  - m-a-p/CodeFeedback-Filtered-Instruction
  - m-a-p/Code-Feedback
language:
  - en
base_model: cognitivecomputations/Dolphin3.0-Qwen2.5-3b
tags:
  - mlx

CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q4-mlx

The Model CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q4-mlx was converted to MLX format from cognitivecomputations/Dolphin3.0-Qwen2.5-3b using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q4-mlx")

prompt="hello"

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

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