metadata
base_model: Kortix/FastApply-7B-v1.0
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
- fast-apply
- instant-apply
- mlx
- mlx-my-repo
dangerusslee/FastApply-7B-v1.0-mlx-4Bit
The Model dangerusslee/FastApply-7B-v1.0-mlx-4Bit was converted to MLX format from Kortix/FastApply-7B-v1.0 using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("dangerusslee/FastApply-7B-v1.0-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)