Hugging Face's logo

tensorblock
/
cyber-risk-llama-3-8b-instruct-sft-GGUF

Text Generation
GGUF
finance
supervision
cyber risk
cybersecurity
cyber threats
SFT
LoRA
A100GPU
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
cyber-risk-llama-3-8b-instruct-sft-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
c6ad878 verified
preview code
|
raw
history blame contribute delete
5.65 kB
metadata
datasets:
  - Vanessasml/cybersecurity_32k_instruction_input_output
pipeline_tag: text-generation
tags:
  - finance
  - supervision
  - cyber risk
  - cybersecurity
  - cyber threats
  - SFT
  - LoRA
  - A100GPU
  - TensorBlock
  - GGUF
base_model: Vanessasml/cyber-risk-llama-3-8b-instruct-sft
TensorBlock

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

Vanessasml/cyber-risk-llama-3-8b-instruct-sft - GGUF

This repo contains GGUF format model files for Vanessasml/cyber-risk-llama-3-8b-instruct-sft.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
cyber-risk-llama-3-8b-instruct-sft-Q2_K.gguf Q2_K 3.179 GB smallest, significant quality loss - not recommended for most purposes
cyber-risk-llama-3-8b-instruct-sft-Q3_K_S.gguf Q3_K_S 3.665 GB very small, high quality loss
cyber-risk-llama-3-8b-instruct-sft-Q3_K_M.gguf Q3_K_M 4.019 GB very small, high quality loss
cyber-risk-llama-3-8b-instruct-sft-Q3_K_L.gguf Q3_K_L 4.322 GB small, substantial quality loss
cyber-risk-llama-3-8b-instruct-sft-Q4_0.gguf Q4_0 4.661 GB legacy; small, very high quality loss - prefer using Q3_K_M
cyber-risk-llama-3-8b-instruct-sft-Q4_K_S.gguf Q4_K_S 4.693 GB small, greater quality loss
cyber-risk-llama-3-8b-instruct-sft-Q4_K_M.gguf Q4_K_M 4.921 GB medium, balanced quality - recommended
cyber-risk-llama-3-8b-instruct-sft-Q5_0.gguf Q5_0 5.599 GB legacy; medium, balanced quality - prefer using Q4_K_M
cyber-risk-llama-3-8b-instruct-sft-Q5_K_S.gguf Q5_K_S 5.599 GB large, low quality loss - recommended
cyber-risk-llama-3-8b-instruct-sft-Q5_K_M.gguf Q5_K_M 5.733 GB large, very low quality loss - recommended
cyber-risk-llama-3-8b-instruct-sft-Q6_K.gguf Q6_K 6.596 GB very large, extremely low quality loss
cyber-risk-llama-3-8b-instruct-sft-Q8_0.gguf Q8_0 8.541 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/cyber-risk-llama-3-8b-instruct-sft-GGUF --include "cyber-risk-llama-3-8b-instruct-sft-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/cyber-risk-llama-3-8b-instruct-sft-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'