metadata
license: apache-2.0
language:
- en
base_model: prithivMLmods/Blitzar-Coder-4B-F.1
pipeline_tag: text-generation
library_name: transformers
tags:
- code
- RL
- text-generation-inference
- mot
- moe
- <think>
- mlx
- mlx-my-repo
datasets:
- livecodebench/code_generation_lite
- PrimeIntellect/verifiable-coding-problems
- likaixin/TACO-verified
- open-r1/codeforces-cots
cof139/Blitzar-Coder-4B-F.1-mlx-4Bit
The Model cof139/Blitzar-Coder-4B-F.1-mlx-4Bit was converted to MLX format from prithivMLmods/Blitzar-Coder-4B-F.1 using mlx-lm version 0.25.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cof139/Blitzar-Coder-4B-F.1-mlx-4Bit")
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)