README.md

metadata

language:
  - en
license: mit
base_model:
  - mistralai/Mistral-7B-v0.1
datasets:
  - argilla/distilabel-capybara-dpo-7k-binarized
pipeline_tag: text-generation
model-index:
  - name: Mistral-ORPO-Capybara-7k
    results:
      - task:
          type: text-generation
        dataset:
          name: AlpacaEval 2 (LC)
          type: AlpacaEval
        metrics:
          - type: AlpacaEval 2.0
            value: 15.88%
            name: Win Rate
        source:
          url: https://tatsu-lab.github.io/alpaca_eval/
          name: self-reported
      - task:
          type: text-generation
        dataset:
          name: MT-Bench
          type: MT-Bench
        metrics:
          - type: MT-Bench
            value: 7.444
            name: Score
        source:
          url: https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/
          name: self-reported
quantized_by: bartowski

Llamacpp Quantizations of mistral-orpo-capybara-7k

Using llama.cpp release b2440 for quantization.

Original model: https://huggingface.co/kaist-ai/mistral-orpo-capybara-7k

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
mistral-orpo-capybara-7k-Q8_0.gguf	Q8_0	7.69GB	Extremely high quality, generally unneeded but max available quant.
mistral-orpo-capybara-7k-Q6_K.gguf	Q6_K	5.94GB	Very high quality, near perfect, recommended.
mistral-orpo-capybara-7k-Q5_K_M.gguf	Q5_K_M	5.13GB	High quality, very usable.
mistral-orpo-capybara-7k-Q5_K_S.gguf	Q5_K_S	4.99GB	High quality, very usable.
mistral-orpo-capybara-7k-Q5_0.gguf	Q5_0	4.99GB	High quality, older format, generally not recommended.
mistral-orpo-capybara-7k-Q4_K_M.gguf	Q4_K_M	4.36GB	Good quality, similar to 4.25 bpw.
mistral-orpo-capybara-7k-Q4_K_S.gguf	Q4_K_S	4.14GB	Slightly lower quality with small space savings.
mistral-orpo-capybara-7k-IQ4_NL.gguf	IQ4_NL	4.15GB	Good quality, similar to Q4_K_S, new method of quanting,
mistral-orpo-capybara-7k-IQ4_XS.gguf	IQ4_XS	3.94GB	Decent quality, new method with similar performance to Q4.
mistral-orpo-capybara-7k-Q4_0.gguf	Q4_0	4.10GB	Decent quality, older format, generally not recommended.
mistral-orpo-capybara-7k-IQ3_M.gguf	IQ3_M	3.28GB	Medium-low quality, new method with decent performance.
mistral-orpo-capybara-7k-IQ3_S.gguf	IQ3_S	3.18GB	Lower quality, new method with decent performance, recommended over Q3 quants.
mistral-orpo-capybara-7k-Q3_K_L.gguf	Q3_K_L	3.82GB	Lower quality but usable, good for low RAM availability.
mistral-orpo-capybara-7k-Q3_K_M.gguf	Q3_K_M	3.51GB	Even lower quality.
mistral-orpo-capybara-7k-Q3_K_S.gguf	Q3_K_S	3.16GB	Low quality, not recommended.
mistral-orpo-capybara-7k-Q2_K.gguf	Q2_K	2.71GB	Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski