README.md

metadata

language:
  - en
datasets:
  - tiiuae/falcon-refinedweb
  - HuggingFaceFW/fineweb-edu
license: other
license_name: falcon-mamba-7b-license
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
base_model: tiiuae/falcon-mamba-7b
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: falcon-mamba-7b
    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: 33.36
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          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: 19.88
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          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: 3.63
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          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: 8.05
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          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: 10.86
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          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: 14.47
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
          name: Open LLM Leaderboard

tiiuae/falcon-mamba-7b - GGUF

This repo contains GGUF format model files for tiiuae/falcon-mamba-7b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
falcon-mamba-7b-Q2_K.gguf	Q2_K	2.389 GB	smallest, significant quality loss - not recommended for most purposes
falcon-mamba-7b-Q3_K_S.gguf	Q3_K_S	3.050 GB	very small, high quality loss
falcon-mamba-7b-Q3_K_M.gguf	Q3_K_M	3.050 GB	very small, high quality loss
falcon-mamba-7b-Q3_K_L.gguf	Q3_K_L	3.050 GB	small, substantial quality loss
falcon-mamba-7b-Q4_0.gguf	Q4_0	3.915 GB	legacy; small, very high quality loss - prefer using Q3_K_M
falcon-mamba-7b-Q4_K_S.gguf	Q4_K_S	3.915 GB	small, greater quality loss
falcon-mamba-7b-Q4_K_M.gguf	Q4_K_M	3.915 GB	medium, balanced quality - recommended
falcon-mamba-7b-Q5_0.gguf	Q5_0	4.730 GB	legacy; medium, balanced quality - prefer using Q4_K_M
falcon-mamba-7b-Q5_K_S.gguf	Q5_K_S	4.730 GB	large, low quality loss - recommended
falcon-mamba-7b-Q5_K_M.gguf	Q5_K_M	4.730 GB	large, very low quality loss - recommended
falcon-mamba-7b-Q6_K.gguf	Q6_K	5.595 GB	very large, extremely low quality loss
falcon-mamba-7b-Q8_0.gguf	Q8_0	7.232 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/falcon-mamba-7b-GGUF --include "falcon-mamba-7b-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/falcon-mamba-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'