README.md

metadata

base_model: byroneverson/Yi-1.5-34B-Chat-abliterated
license: apache-2.0
pipeline_tag: text-generation
language:
  - zh
  - en
tags:
  - llm
  - long context
  - yi
  - chat
  - it
  - abliterated
  - mlx
  - mlx-my-repo
library_name: transformers

Fmuaddib/Yi-1.5-34B-Chat-abliterated-mlx-4Bit

The Model Fmuaddib/Yi-1.5-34B-Chat-abliterated-mlx-4Bit was converted to MLX format from byroneverson/Yi-1.5-34B-Chat-abliterated using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/Yi-1.5-34B-Chat-abliterated-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)