change max_new_tokens 192
55cf6ae
Roman
commited on
Commit History
change max_new_tokens to 256
298f5d9
Roman
commited on
change model to Gensyn/Qwen2.5-0.5B-Instruct
bd5778d
Roman
commited on
update app.py code
00e9430
Roman
commited on
add progressbar
21472e6
Roman
commited on
change max_new_tokens to 192
dff1278
Roman
commited on
change model to google/flan-t5-base
9d58e14
Roman
commited on
return readme file content
bed052c
Roman
commited on
update readme
5d617f2
Roman
commited on
change model to tiiuae/falcon-1b
e28d9aa
Roman
commited on
change model to deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
bac4bb8
Roman
commited on
change model to HuggingFaceH4/zephyr-7b-beta
b886971
Roman
commited on
change model to mistralai/Mistral-7B-Instruct-v0.2
66764ae
Roman
commited on
add gradio to project
5fd0144
Roman
commited on
change model to distilbert/distilgpt2
974b159
Roman
commited on
add torch to requirements.txt
c849aa7
Roman
commited on
change model to distilgpt2
ccc507c
Roman
commited on
remove model device_map, torch_dtype
d7ee72d
Roman
commited on
change model to HuggingFaceH4/zephyr-7b-beta
88606cc
Roman
commited on
change model to Mistral-7B-OpenOrca
b7bfc34
Roman
commited on
use Mistral-7B-Instruct-v0.2 model
602834e
Roman
commited on
init
d957432
Roman
commited on