GGUF
Telugu
English
TensorBlock
GGUF
Inference Endpoints
conversational
TensorBlock

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

Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct - GGUF

This repo contains GGUF format model files for Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct.

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

Prompt template

<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Model file specification

Filename Quant type File Size Description
Telugu-Llama2-7B-v0-Instruct-Q2_K.gguf Q2_K 2.533 GB smallest, significant quality loss - not recommended for most purposes
Telugu-Llama2-7B-v0-Instruct-Q3_K_S.gguf Q3_K_S 2.948 GB very small, high quality loss
Telugu-Llama2-7B-v0-Instruct-Q3_K_M.gguf Q3_K_M 3.298 GB very small, high quality loss
Telugu-Llama2-7B-v0-Instruct-Q3_K_L.gguf Q3_K_L 3.597 GB small, substantial quality loss
Telugu-Llama2-7B-v0-Instruct-Q4_0.gguf Q4_0 3.826 GB legacy; small, very high quality loss - prefer using Q3_K_M
Telugu-Llama2-7B-v0-Instruct-Q4_K_S.gguf Q4_K_S 3.857 GB small, greater quality loss
Telugu-Llama2-7B-v0-Instruct-Q4_K_M.gguf Q4_K_M 4.081 GB medium, balanced quality - recommended
Telugu-Llama2-7B-v0-Instruct-Q5_0.gguf Q5_0 4.652 GB legacy; medium, balanced quality - prefer using Q4_K_M
Telugu-Llama2-7B-v0-Instruct-Q5_K_S.gguf Q5_K_S 4.652 GB large, low quality loss - recommended
Telugu-Llama2-7B-v0-Instruct-Q5_K_M.gguf Q5_K_M 4.783 GB large, very low quality loss - recommended
Telugu-Llama2-7B-v0-Instruct-Q6_K.gguf Q6_K 5.529 GB very large, extremely low quality loss
Telugu-Llama2-7B-v0-Instruct-Q8_0.gguf Q8_0 7.161 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/Telugu-Llama2-7B-v0-Instruct-GGUF --include "Telugu-Llama2-7B-v0-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/Telugu-Llama2-7B-v0-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
177
GGUF
Model size
6.74B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/Telugu-Llama2-7B-v0-Instruct-GGUF

Quantized
(1)
this model

Datasets used to train tensorblock/Telugu-Llama2-7B-v0-Instruct-GGUF