Hugging Face's logo

tensorblock
/
TinyLlama-1.1B-32k-Instruct-GGUF

Text Generation
Transformers
GGUF
English
llama
TensorBlock
GGUF
conversational
Model card Files Community
TinyLlama-1.1B-32k-Instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
768e182 verified
preview code
|
raw
history blame contribute delete
5.45 kB
metadata
inference: false
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - llama
  - TensorBlock
  - GGUF
datasets:
  - LDJnr/Capybara
  - jondurbin/airoboros-3.2
  - unalignment/toxic-dpo-v0.1
  - LDJnr/Verified-Camel
  - HuggingFaceH4/no_robots
  - Doctor-Shotgun/no-robots-sharegpt
  - Doctor-Shotgun/capybara-sharegpt
base_model: Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
TensorBlock

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

Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct - GGUF

This repo contains GGUF format model files for Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct.

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

Prompt template 

<s>
### Instruction:
{system_prompt}

### Input:
{prompt}

### Response:

Model file specification

Filename Quant type File Size Description
TinyLlama-1.1B-32k-Instruct-Q2_K.gguf Q2_K 0.402 GB smallest, significant quality loss - not recommended for most purposes
TinyLlama-1.1B-32k-Instruct-Q3_K_S.gguf Q3_K_S 0.465 GB very small, high quality loss
TinyLlama-1.1B-32k-Instruct-Q3_K_M.gguf Q3_K_M 0.511 GB very small, high quality loss
TinyLlama-1.1B-32k-Instruct-Q3_K_L.gguf Q3_K_L 0.551 GB small, substantial quality loss
TinyLlama-1.1B-32k-Instruct-Q4_0.gguf Q4_0 0.593 GB legacy; small, very high quality loss - prefer using Q3_K_M
TinyLlama-1.1B-32k-Instruct-Q4_K_S.gguf Q4_K_S 0.596 GB small, greater quality loss
TinyLlama-1.1B-32k-Instruct-Q4_K_M.gguf Q4_K_M 0.622 GB medium, balanced quality - recommended
TinyLlama-1.1B-32k-Instruct-Q5_0.gguf Q5_0 0.713 GB legacy; medium, balanced quality - prefer using Q4_K_M
TinyLlama-1.1B-32k-Instruct-Q5_K_S.gguf Q5_K_S 0.713 GB large, low quality loss - recommended
TinyLlama-1.1B-32k-Instruct-Q5_K_M.gguf Q5_K_M 0.728 GB large, very low quality loss - recommended
TinyLlama-1.1B-32k-Instruct-Q6_K.gguf Q6_K 0.841 GB very large, extremely low quality loss
TinyLlama-1.1B-32k-Instruct-Q8_0.gguf Q8_0 1.089 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/TinyLlama-1.1B-32k-Instruct-GGUF --include "TinyLlama-1.1B-32k-Instruct-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/TinyLlama-1.1B-32k-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'