README.md

metadata

language:
  - fr
  - it
  - de
  - es
  - en
license: apache-2.0
tags:
  - moe
  - TensorBlock
  - GGUF
base_model: cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
model-index:
  - name: Mixtral-8x7B-Instruct-v0.1-DPO
    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: 69.8
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          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: 87.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          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: 71.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          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: 69.18
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          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: 81.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          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: 61.41
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          name: Open LLM Leaderboard

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO - GGUF

This repo contains GGUF format model files for cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<s>[INST] {prompt} [/INST]

Model file specification

Filename	Quant type	File Size	Description
Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf	Q2_K	17.311 GB	smallest, significant quality loss - not recommended for most purposes
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf	Q3_K_S	20.433 GB	very small, high quality loss
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf	Q3_K_M	22.546 GB	very small, high quality loss
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf	Q3_K_L	24.170 GB	small, substantial quality loss
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf	Q4_0	26.444 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf	Q4_K_S	26.746 GB	small, greater quality loss
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf	Q4_K_M	28.448 GB	medium, balanced quality - recommended
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf	Q5_0	32.231 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf	Q5_K_S	32.231 GB	large, low quality loss - recommended
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf	Q5_K_M	33.230 GB	large, very low quality loss - recommended
Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf	Q6_K	38.381 GB	very large, extremely low quality loss
Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf	Q8_0	49.626 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF --include "Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'