README.md

metadata

language:
  - zh
  - en
  - fr
  - de
  - ja
  - ko
  - it
  - ru
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
inference: false
tags:
  - TensorBlock
  - GGUF
base_model: OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
model-index:
  - name: openbuddy-mixtral-7bx8-v18.1-32k
    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: 67.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          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: 84.3
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          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: 70.94
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          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: 56.72
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          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: 80.98
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          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: 65.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
          name: Open LLM Leaderboard

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

OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k - GGUF

This repo contains GGUF format model files for OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k.

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

{system_prompt}
User: {prompt}
Assistant:

Model file specification

Filename	Quant type	File Size	Description
openbuddy-mixtral-7bx8-v18.1-32k-Q2_K.gguf	Q2_K	17.333 GB	smallest, significant quality loss - not recommended for most purposes
openbuddy-mixtral-7bx8-v18.1-32k-Q3_K_S.gguf	Q3_K_S	20.456 GB	very small, high quality loss
openbuddy-mixtral-7bx8-v18.1-32k-Q3_K_M.gguf	Q3_K_M	22.570 GB	very small, high quality loss
openbuddy-mixtral-7bx8-v18.1-32k-Q3_K_L.gguf	Q3_K_L	24.193 GB	small, substantial quality loss
openbuddy-mixtral-7bx8-v18.1-32k-Q4_0.gguf	Q4_0	26.470 GB	legacy; small, very high quality loss - prefer using Q3_K_M
openbuddy-mixtral-7bx8-v18.1-32k-Q4_K_S.gguf	Q4_K_S	26.772 GB	small, greater quality loss
openbuddy-mixtral-7bx8-v18.1-32k-Q4_K_M.gguf	Q4_K_M	28.475 GB	medium, balanced quality - recommended
openbuddy-mixtral-7bx8-v18.1-32k-Q5_0.gguf	Q5_0	32.260 GB	legacy; medium, balanced quality - prefer using Q4_K_M
openbuddy-mixtral-7bx8-v18.1-32k-Q5_K_S.gguf	Q5_K_S	32.260 GB	large, low quality loss - recommended
openbuddy-mixtral-7bx8-v18.1-32k-Q5_K_M.gguf	Q5_K_M	33.258 GB	large, very low quality loss - recommended
openbuddy-mixtral-7bx8-v18.1-32k-Q6_K.gguf	Q6_K	38.412 GB	very large, extremely low quality loss
openbuddy-mixtral-7bx8-v18.1-32k-Q8_0.gguf	Q8_0	49.667 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/openbuddy-mixtral-7bx8-v18.1-32k-GGUF --include "openbuddy-mixtral-7bx8-v18.1-32k-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/openbuddy-mixtral-7bx8-v18.1-32k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'