Models
GitHub
Discord
Turbo
Sign in
Download
Models
Download
GitHub
Discord
Sign in
vitali87
/
shell-commands
:latest
133
Downloads
Updated
10 months ago
QWen2-based command-line assistant model fine-tuned using LoRA and 4-bit quantization, optimized for generating Unix/Linux commands with a simple prompt format and explicit stop sequences.
QWen2-based command-line assistant model fine-tuned using LoRA and 4-bit quantization, optimized for generating Unix/Linux commands with a simple prompt format and explicit stop sequences.
Cancel
Updated 10 months ago
10 months ago
9f4c23e705ca · 1.6GB
model
arch
qwen2
·
parameters
1.54B
·
quantization
Q8_0
1.6GB
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|>{{ end }}<|im_start|>user {{ .Prompt }}<|i
131B
params
{ "stop": [ "<|im_end|>" ], "temperature": 0, "top_p": 0.7 }
62B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)