Hugging Face's logo

tensorblock
/
falcon-7b-instruct-sharded-GGUF

GGUF
English
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
falcon-7b-instruct-sharded-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
500d111 verified
preview code
|
raw
history blame contribute delete
5.43 kB
metadata
datasets:
  - tiiuae/falcon-refinedweb
language:
  - en
inference: true
widget:
  - text: Hey Falcon! Any recommendations for my holidays in Abu Dhabi?
    example_title: Abu Dhabi Trip
  - text: What's the Everett interpretation of quantum mechanics?
    example_title: 'Q/A: Quantum & Answers'
  - text: >-
      Give me a list of the top 10 dive sites you would recommend around the
      world.
    example_title: Diving Top 10
  - text: Can you tell me more about deep-water soloing?
    example_title: Extreme sports
  - text: >-
      Can you write a short tweet about the Apache 2.0 release of our latest AI
      model, Falcon LLM?
    example_title: Twitter Helper
  - text: What are the responsabilities of a Chief Llama Officer?
    example_title: Trendy Jobs
license: apache-2.0
base_model: vilsonrodrigues/falcon-7b-instruct-sharded
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

vilsonrodrigues/falcon-7b-instruct-sharded - GGUF

This repo contains GGUF format model files for vilsonrodrigues/falcon-7b-instruct-sharded.

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

Prompt template

Model file specification

Filename Quant type File Size Description
falcon-7b-instruct-sharded-Q2_K.gguf Q2_K 3.440 GB smallest, significant quality loss - not recommended for most purposes
falcon-7b-instruct-sharded-Q3_K_S.gguf Q3_K_S 3.440 GB very small, high quality loss
falcon-7b-instruct-sharded-Q3_K_M.gguf Q3_K_M 3.702 GB very small, high quality loss
falcon-7b-instruct-sharded-Q3_K_L.gguf Q3_K_L 3.923 GB small, substantial quality loss
falcon-7b-instruct-sharded-Q4_0.gguf Q4_0 3.767 GB legacy; small, very high quality loss - prefer using Q3_K_M
falcon-7b-instruct-sharded-Q4_K_S.gguf Q4_K_S 4.230 GB small, greater quality loss
falcon-7b-instruct-sharded-Q4_K_M.gguf Q4_K_M 4.444 GB medium, balanced quality - recommended
falcon-7b-instruct-sharded-Q5_0.gguf Q5_0 4.538 GB legacy; medium, balanced quality - prefer using Q4_K_M
falcon-7b-instruct-sharded-Q5_K_S.gguf Q5_K_S 4.770 GB large, low quality loss - recommended
falcon-7b-instruct-sharded-Q5_K_M.gguf Q5_K_M 5.131 GB large, very low quality loss - recommended
falcon-7b-instruct-sharded-Q6_K.gguf Q6_K 6.256 GB very large, extremely low quality loss
falcon-7b-instruct-sharded-Q8_0.gguf Q8_0 6.852 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-7b-instruct-sharded-GGUF --include "falcon-7b-instruct-sharded-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-7b-instruct-sharded-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'