froggeric

froggeric's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in froggeric/Qwen-Fixed-Chat-Templates about 14 hours ago

chat template v21.3

🔥 4

8

#51 opened 1 day ago by

froggeric

updated a model about 14 hours ago

froggeric/Qwen-Fixed-Chat-Templates

Updated about 14 hours ago • 647

New activity in froggeric/Qwen-Fixed-Chat-Templates 1 day ago

Runtime-adaptive tool-call format: XML on vLLM, Hermes JSON on llama.cpp — no config needed

1

#53 opened 1 day ago by

Moore2877

Runtime-adaptive tool-call format: XML on vLLM, Hermes JSON on llama.cpp — no config needed

3

#52 opened 1 day ago by

Moore2877

Keeps emitting <tool_call> json into the context

➕ 1

9

#23 opened about 2 months ago by

theliphant

Breaks claude code

11

#41 opened 23 days ago by

widdae

toolcall inside thinking

👀 3

9

#25 opened about 2 months ago by

snapo

Non-thinking generation prompt uses non-canonical `<think>\n</think>\n` → duplicated output under streaming

6

#43 opened 16 days ago by

batsclamp

Response will sometimes show full thought process to Frigate, which will fail to create a GenAI Summary

2

#27 opened about 1 month ago by

ampersandru

v20 released: C++ AST optimization & minja compatibility patch

👍 10

1

#33 opened 28 days ago by

froggeric

Lmstudio Prompt Template override not available in Server Mode only works in Chat tab

5

#34 opened 28 days ago by

dasss-st

Will this work on spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit ?

8

#32 opened about 1 month ago by

openSourcerer9000

122B-A10B 4bit

1

#35 opened 27 days ago by

O-ishi

Still issues with tooling from time to time....

5

#29 opened about 1 month ago by

boldos

Reasoning off mode issue

👍 3

9

#30 opened about 1 month ago by

GergelyZsolt

preserve_thinking: false or true

👍 1

3

#37 opened 25 days ago by

vikuloff

`</think>` strings appears meaningless in content text

1

#38 opened 24 days ago by

tooltd

v20: Agent looping/repeating actions in agentic workflows

4

#39 opened 24 days ago by

kratto

Remove extra newline that breaks prefix cache after tool calls

2

#42 opened 18 days ago by

choongng

Enhancement: support Anthropic-style `message.thinking` alongside `reasoning_content`

1

#50 opened 2 days ago by

Moore2877