metadata
license: apache-2.0
datasets:
- livecodebench/code_generation_lite
- agentica-org/DeepCoder-Preview-Dataset
- NousResearch/lcb_test
- NousResearch/RLVR_Coding_Problems
base_model: NousResearch/NousCoder-14B
pipeline_tag: text-generation
tags:
- mlx
ncls-p/NousCoder-14B-mlx-6Bit
The Model ncls-p/NousCoder-14B-mlx-6Bit was converted to MLX format from NousResearch/NousCoder-14B using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ncls-p/NousCoder-14B-mlx-6Bit")
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)