README.md

metadata

license: apache-2.0
base_model: speakleash/Bielik-11B-v2.3-Instruct
language:
  - pl
library_name: transformers
tags:
  - merge
  - mergekit
  - mlx
  - mlx-my-repo
inference:
  parameters:
    temperature: 0.2
widget:
  - messages:
      - role: user
        content: Co przedstawia polskie godło?
extra_gated_description: >-
  If you want to learn more about how you can use the model, please refer to our
  <a href="https://bielik.ai/terms/">Terms of Use</a>.

lknik/Bielik-11B-v2.3-Instruct-8bit

The Model lknik/Bielik-11B-v2.3-Instruct-8bit was converted to MLX format from speakleash/Bielik-11B-v2.3-Instruct using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("lknik/Bielik-11B-v2.3-Instruct-8bit")

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)