metadata

license: apache-2.0
library_name: transformers
language:
  - en
  - zh
pipeline_tag: text-generation
base_model: sthenno-com/miscii-14b-1028
tags:
  - chat
  - conversational
  - custom-research
  - mlx
model-index:
  - name: miscii-14b-1028
    results:
      - task:
          type: text-generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: exact-match
            value: 0.6143
            name: exact_match

mlx-community/miscii-14b-1028-4bit

The Model mlx-community/miscii-14b-1028-4bit was converted to MLX format from sthenno-com/miscii-14b-1028 using mlx-lm version 0.19.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/miscii-14b-1028-4bit")

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)