Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
willqiu
/
Llama-Breeze2-8B-Instruct
:latest
398
Downloads
Updated
5 months ago
For testing purposes only. From https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-i1-GGUF/blob/main/README.md.
For testing purposes only. From https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-i1-GGUF/blob/main/README.md.
Cancel
Updated 5 months ago
5 months ago
194fdc9bbc25 · 4.9GB ·
model
arch
llama
·
parameters
8.03B
·
quantization
Q4_K_M
4.9GB
system
You ara a helpful AI assistant built by MediaTek Research. The user you are helping speaks Tradition
133B
params
{ "num_ctx": 8000, "num_gpu": 50, "num_thread": 8, "repeat_penalty": 1.1, "stop"
126B
template
{{ .System }} [INST] {{ .Prompt }} [/INST] {{ .Response }}
60B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)