README.md

metadata

base_model: Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
datasets:
  - LDJnr/Capybara
  - jondurbin/airoboros-3.2
  - unalignment/toxic-dpo-v0.1
  - LDJnr/Verified-Camel
  - HuggingFaceH4/no_robots
  - Doctor-Shotgun/no-robots-sharegpt
  - Doctor-Shotgun/capybara-sharegpt
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - llama
  - mlx
inference: false

vrglx33/TinyLlama-1.1B-32k-Instruct-mlx

The Model vrglx33/TinyLlama-1.1B-32k-Instruct-mlx was converted to MLX format from Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct using mlx-lm version 0.19.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("vrglx33/TinyLlama-1.1B-32k-Instruct-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)