Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
maxkerkula
/
megabeam-mistral-7b-512k-q6_k_l
:latest
125
Downloads
Updated
1 year ago
Cancel
Updated 1 year ago
1 year ago
7a5d7d26ae21 · 6.0GB ·
model
arch
llama
·
parameters
7.24B
·
quantization
Q6_K
6.0GB
system
You are an AI assistant based on the MegaBeam-Mistral-7B-512k model. You are helpful, honest, and ha
107B
params
{ "num_ctx": 8192, "stop": [ "<|im_start|>", "<|im_end|>" ], "temper
104B
template
[INST] {{.System}} {{.Prompt}} [/INST]
38B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)