README.md

metadata

license: apache-2.0
language:
  - en
base_model: FuseAI/FuseChat-7B-VaRM
datasets:
  - FuseAI/FuseChat-Mixture
pipeline_tag: text-generation
tags:
  - mistral
  - mixtral
  - solar
  - model-fusion
  - fusechat
  - TensorBlock
  - GGUF
library_name: transformers
model-index:
  - name: FuseChat-7B-VaRM
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MT-Bench
          type: unknown
        metrics:
          - type: unknown
            value: 8.22
            name: score
        source:
          url: https://huggingface.co/spaces/lmsys/mt-bench
      - 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: 62.88
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          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: 84.25
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          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: 63.71
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          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: 45.67
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          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: 79.16
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          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: 63.46
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FuseAI/FuseChat-7B-VaRM
          name: Open LLM Leaderboard

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

FuseAI/FuseChat-7B-VaRM - GGUF

This repo contains GGUF format model files for FuseAI/FuseChat-7B-VaRM.

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>GPT4 Correct System: {system_prompt}<|end_of_turn|>GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:

Model file specification

Filename	Quant type	File Size	Description
FuseChat-7B-VaRM-Q2_K.gguf	Q2_K	2.719 GB	smallest, significant quality loss - not recommended for most purposes
FuseChat-7B-VaRM-Q3_K_S.gguf	Q3_K_S	3.165 GB	very small, high quality loss
FuseChat-7B-VaRM-Q3_K_M.gguf	Q3_K_M	3.519 GB	very small, high quality loss
FuseChat-7B-VaRM-Q3_K_L.gguf	Q3_K_L	3.822 GB	small, substantial quality loss
FuseChat-7B-VaRM-Q4_0.gguf	Q4_0	4.109 GB	legacy; small, very high quality loss - prefer using Q3_K_M
FuseChat-7B-VaRM-Q4_K_S.gguf	Q4_K_S	4.140 GB	small, greater quality loss
FuseChat-7B-VaRM-Q4_K_M.gguf	Q4_K_M	4.368 GB	medium, balanced quality - recommended
FuseChat-7B-VaRM-Q5_0.gguf	Q5_0	4.998 GB	legacy; medium, balanced quality - prefer using Q4_K_M
FuseChat-7B-VaRM-Q5_K_S.gguf	Q5_K_S	4.998 GB	large, low quality loss - recommended
FuseChat-7B-VaRM-Q5_K_M.gguf	Q5_K_M	5.131 GB	large, very low quality loss - recommended
FuseChat-7B-VaRM-Q6_K.gguf	Q6_K	5.942 GB	very large, extremely low quality loss
FuseChat-7B-VaRM-Q8_0.gguf	Q8_0	7.696 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/FuseChat-7B-VaRM-GGUF --include "FuseChat-7B-VaRM-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/FuseChat-7B-VaRM-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'