README.md

metadata

language:
  - en
license: apache-2.0
pipeline_tag: text-generation
tags:
  - TensorBlock
  - GGUF
base_model: tensoropera/Fox-1-1.6B
model-index:
  - name: Fox-1-1.6B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 27.66
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 7.4
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 1.28
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 1.79
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 3.87
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 4.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tensoropera/Fox-1-1.6B
          name: Open LLM Leaderboard

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

tensoropera/Fox-1-1.6B - GGUF

This repo contains GGUF format model files for tensoropera/Fox-1-1.6B.

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|>
{system_prompt}<eos>
<|user|>
{prompt}<eos>
<|assistant|>

Model file specification

Filename	Quant type	File Size	Description
Fox-1-1.6B-Q2_K.gguf	Q2_K	0.860 GB	smallest, significant quality loss - not recommended for most purposes
Fox-1-1.6B-Q3_K_S.gguf	Q3_K_S	0.927 GB	very small, high quality loss
Fox-1-1.6B-Q3_K_M.gguf	Q3_K_M	0.987 GB	very small, high quality loss
Fox-1-1.6B-Q3_K_L.gguf	Q3_K_L	1.039 GB	small, substantial quality loss
Fox-1-1.6B-Q4_0.gguf	Q4_0	1.078 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Fox-1-1.6B-Q4_K_S.gguf	Q4_K_S	1.083 GB	small, greater quality loss
Fox-1-1.6B-Q4_K_M.gguf	Q4_K_M	1.117 GB	medium, balanced quality - recommended
Fox-1-1.6B-Q5_0.gguf	Q5_0	1.221 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Fox-1-1.6B-Q5_K_S.gguf	Q5_K_S	1.221 GB	large, low quality loss - recommended
Fox-1-1.6B-Q5_K_M.gguf	Q5_K_M	1.241 GB	large, very low quality loss - recommended
Fox-1-1.6B-Q6_K.gguf	Q6_K	1.373 GB	very large, extremely low quality loss
Fox-1-1.6B-Q8_0.gguf	Q8_0	1.776 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/Fox-1-1.6B-GGUF --include "Fox-1-1.6B-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/Fox-1-1.6B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'