You can deploy this model and start earning money today!

tensorblock/
test-llama-2-70b-chat-hf-GGUF

Name: test-llama-2-70b-chat-hf-GGUF
Availability: InStock

Views

No views yet

JasonFuriosa/test-llama-2-70b-chat-hf - GGUF

This repo contains GGUF format model files for JasonFuriosa/test-llama-2-70b-chat-hf.

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

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
MCP Servers	Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Filename	Quant type	File Size	Description
test-llama-2-70b-chat-hf-Q2_K.gguf	Q2_K	0.615 GB	smallest, significant quality loss - not recommended for most purposes
test-llama-2-70b-chat-hf-Q3_K_S.gguf	Q3_K_S	0.696 GB	very small, high quality loss
test-llama-2-70b-chat-hf-Q3_K_M.gguf	Q3_K_M	0.738 GB	very small, high quality loss
test-llama-2-70b-chat-hf-Q3_K_L.gguf	Q3_K_L	0.776 GB	small, substantial quality loss
test-llama-2-70b-chat-hf-Q4_0.gguf	Q4_0	0.845 GB	legacy; small, very high quality loss - prefer using Q3_K_M
test-llama-2-70b-chat-hf-Q4_K_S.gguf	Q4_K_S	0.846 GB	small, greater quality loss
test-llama-2-70b-chat-hf-Q4_K_M.gguf	Q4_K_M	0.907 GB	medium, balanced quality - recommended
test-llama-2-70b-chat-hf-Q5_0.gguf	Q5_0	0.984 GB	legacy; medium, balanced quality - prefer using Q4_K_M
test-llama-2-70b-chat-hf-Q5_K_S.gguf	Q5_K_S	0.984 GB	large, low quality loss - recommended
test-llama-2-70b-chat-hf-Q5_K_M.gguf	Q5_K_M	1.017 GB	large, very low quality loss - recommended
test-llama-2-70b-chat-hf-Q6_K.gguf	Q6_K	1.133 GB	very large, extremely low quality loss
test-llama-2-70b-chat-hf-Q8_0.gguf	Q8_0	1.467 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/test-llama-2-70b-chat-hf-GGUF --include "test-llama-2-70b-chat-hf-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/test-llama-2-70b-chat-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'