Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Preferred Networks, Inc.
company
Verified
Activity Feed
Follow
265
AI & ML interests
None defined yet.
Recent Activity
sokada
updated
a collection
5 days ago
financial
shemmipfn
new
activity
6 days ago
pfnet/plamo-3-610m-fin-instruct:
Wire enable_thinking through to the assistant generation prompt The generation-prompt call site passed allow_reasoning=True unconditionally, so the enable_thinking chat-template kwarg never changed the assistant header, and the prompt always advertised think support. The call site now reads the enable_thinking template variable: assistant_role_message_header( allow_reasoning=(enable_thinking if enable_thinking is defined else true), allow_tool_request=tools) Default behavior is unchanged: when enable_thinking is not supplied (or true), think is advertised as before. Assistant history rendering keeps allow_reasoning=True; only the generation prompt is affected. Verified against vLLM: resolve_chat_template_kwargs forwards enable_thinking to the template, and the PLaMo3 reasoning parser consumes the same kwarg, so the prompt header and the parser agree on whether reasoning is enabled.
shemmipfn
new
activity
6 days ago
pfnet/plamo-3-610m-fin-instruct:
Wire enable_thinking through to the assistant generation prompt
View all activity
Team members
42
+8
pfnet
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Articles
sokada
updated
a collection
5 days ago
financial
Collection
8 items
•
Updated
5 days ago
shemmipfn
in
pfnet/plamo-3-610m-fin-instruct
6 days ago
Wire enable_thinking through to the assistant generation prompt The generation-prompt call site passed allow_reasoning=True unconditionally, so the enable_thinking chat-template kwarg never changed the assistant header, and the prompt always advertised think support. The call site now reads the enable_thinking template variable: assistant_role_message_header( allow_reasoning=(enable_thinking if enable_thinking is defined else true), allow_tool_request=tools) Default behavior is unchanged: when enable_thinking is not supplied (or true), think is advertised as before. Assistant history rendering keeps allow_reasoning=True; only the generation prompt is affected. Verified against vLLM: resolve_chat_template_kwargs forwards enable_thinking to the template, and the PLaMo3 reasoning parser consumes the same kwarg, so the prompt header and the parser agree on whether reasoning is enabled.
#3 opened 6 days ago by
shemmipfn
Wire enable_thinking through to the assistant generation prompt
1
#2 opened 6 days ago by
shemmipfn
ryocci
published
a model
10 days ago
pfnet/plamo-3-610m-fin-instruct
Text Generation
•
0.9B
•
Updated
10 days ago
•
439
•
4
ryocci
updated
a model
10 days ago
pfnet/plamo-3-610m-fin-instruct
Text Generation
•
0.9B
•
Updated
10 days ago
•
439
•
4
mhiroaki-pfn
published
a dataset
about 1 month ago
pfnet/japanese-mail-bench
Viewer
•
Updated
Aug 31
•
500
•
131
•
3
mhiroaki-pfn
updated
a dataset
about 1 month ago
pfnet/japanese-mail-bench
Viewer
•
Updated
Aug 31
•
500
•
131
•
3
yhirokawa
in
pfnet/plamo-3-nict-2604-31b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#2 opened about 1 month ago by
shemmipfn
yhirokawa
in
pfnet/plamo-3-nict-31b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#1 opened about 1 month ago by
shemmipfn
yhirokawa
in
pfnet/plamo-3-nict-8b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#6 opened about 1 month ago by
shemmipfn
yhirokawa
in
pfnet/plamo-3-nict-2b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#1 opened about 1 month ago by
shemmipfn
shemmipfn
in
pfnet/plamo-3-nict-2b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#1 opened about 1 month ago by
shemmipfn
shemmipfn
in
pfnet/plamo-3-nict-8b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#6 opened about 1 month ago by
shemmipfn
shemmipfn
in
pfnet/plamo-3-nict-31b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#1 opened about 1 month ago by
shemmipfn
shemmipfn
in
pfnet/plamo-3-nict-2604-31b-base
about 1 month ago
Sync unified PLaMo 3 tokenizer implementation
1
#2 opened about 1 month ago by
shemmipfn
Support XGrammer in SGLang
#1 opened about 1 month ago by
shemmipfn
yhirokawa
updated
a collection
3 months ago
PLaMo 3
Collection
4 items
•
Updated
Jul 10
•
1
quant12
published
a model
3 months ago
pfnet/plamo-3-nict-2604-31b-base
Text Generation
•
32B
•
Updated
Aug 21
•
147
•
7
quant12
updated
a model
3 months ago
pfnet/plamo-3-nict-2604-31b-base
Text Generation
•
32B
•
Updated
Aug 21
•
147
•
7
YichongEric
updated
a model
4 months ago
pfnet/GenerRNA
Text Generation
•
Updated
Jun 5
•
7
Load more