README.md

metadata

base_model: karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
datasets:
  - databricks/databricks-dolly-15k
  - glaiveai/glaive-code-assistant-v3
  - glaiveai/glaive-function-calling-v2
  - gretelai/synthetic_text_to_sql
  - meta-math/MetaMathQA
  - microsoft/orca-math-word-problems-200k
  - neural-bridge/rag-dataset-12000
  - neural-bridge/rag-hallucination-dataset-1000
  - nvidia/HelpSteer
  - OpenAssistant/oasst2
language:
  - en
  - ja
library_name: transformers
license: apache-2.0
tags:
  - mixtral
  - steerlm
  - mlx

mlx-community/karakuri-lm-8x7b-instruct-v0.1-4bit

The Model mlx-community/karakuri-lm-8x7b-instruct-v0.1-4bit was converted to MLX format from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1 using mlx-lm version 0.19.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/karakuri-lm-8x7b-instruct-v0.1-4bit")

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)