Hugging Face's logo

tensorblock
/
llama_16bit_2-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
llama
trl
sft
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
llama_16bit_2-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
8bf40bf verified
preview code
|
raw
history blame contribute delete
4.82 kB
metadata
base_model: Sasmitah/llama_16bit_2
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - TensorBlock
  - GGUF
TensorBlock

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

Sasmitah/llama_16bit_2 - GGUF

This repo contains GGUF format model files for Sasmitah/llama_16bit_2.

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

Prompt template 

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 26 July 2024

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename Quant type File Size Description
llama_16bit_2-Q2_K.gguf Q2_K 0.581 GB smallest, significant quality loss - not recommended for most purposes
llama_16bit_2-Q3_K_S.gguf Q3_K_S 0.642 GB very small, high quality loss
llama_16bit_2-Q3_K_M.gguf Q3_K_M 0.691 GB very small, high quality loss
llama_16bit_2-Q3_K_L.gguf Q3_K_L 0.733 GB small, substantial quality loss
llama_16bit_2-Q4_0.gguf Q4_0 0.771 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama_16bit_2-Q4_K_S.gguf Q4_K_S 0.776 GB small, greater quality loss
llama_16bit_2-Q4_K_M.gguf Q4_K_M 0.808 GB medium, balanced quality - recommended
llama_16bit_2-Q5_0.gguf Q5_0 0.893 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama_16bit_2-Q5_K_S.gguf Q5_K_S 0.893 GB large, low quality loss - recommended
llama_16bit_2-Q5_K_M.gguf Q5_K_M 0.912 GB large, very low quality loss - recommended
llama_16bit_2-Q6_K.gguf Q6_K 1.022 GB very large, extremely low quality loss
llama_16bit_2-Q8_0.gguf Q8_0 1.321 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/llama_16bit_2-GGUF --include "llama_16bit_2-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/llama_16bit_2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'