alexgusevski's picture
Upload README.md with huggingface_hub
a63b22c verified
metadata
language:
  - en
license: apache-2.0
library_name: trl
tags:
  - distilabel
  - dpo
  - rlaif
  - rlhf
  - mlx
  - mlx-my-repo
datasets:
  - argilla/dpo-mix-7k
base_model: argilla/CapybaraHermes-2.5-Mistral-7B
model-index:
  - name: CapybaraHermes-2.5-Mistral-7B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 65.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 85.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 63.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 56.91
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 78.3
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 59.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
          name: Open LLM Leaderboard

alexgusevski/CapybaraHermes-2.5-Mistral-7B-mlx-3Bit

The Model alexgusevski/CapybaraHermes-2.5-Mistral-7B-mlx-3Bit was converted to MLX format from argilla/CapybaraHermes-2.5-Mistral-7B using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/CapybaraHermes-2.5-Mistral-7B-mlx-3Bit")

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)