26 lines
561 B
Plaintext
26 lines
561 B
Plaintext
|
# MODELFILE for Qwen3-8B-GGUF
|
||
|
|
# Used by LM Studio, OpenWebUI, GPT4All, etc.
|
||
|
|
|
||
|
|
context_length: 32768
|
||
|
|
embedding: false
|
||
|
|
f16: cpu
|
||
|
|
|
||
|
|
# Chat template using ChatML (used by Qwen)
|
||
|
|
prompt_template: >-
|
||
|
|
<|im_start|>system
|
||
|
|
You are a helpful assistant.<|im_end|>
|
||
|
|
<|im_start|>user
|
||
|
|
{prompt}<|im_end|>
|
||
|
|
<|im_start|>assistant
|
||
|
|
|
||
|
|
# Stop sequences help end generation cleanly
|
||
|
|
stop: "<|im_end|>"
|
||
|
|
stop: "<|im_start|>"
|
||
|
|
|
||
|
|
# Default sampling (optimized for thinking mode)
|
||
|
|
temperature: 0.6
|
||
|
|
top_p: 0.95
|
||
|
|
top_k: 20
|
||
|
|
min_p: 0.0
|
||
|
|
repeat_penalty: 1.1
|