Andrew Moore

Moore2877's activity

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

New activity in Moore2877/Qwen-Fixed-Chat-Templates-llamacpp about 11 hours ago

merge with froggeric

1

#6 opened about 11 hours ago by

l0rdraiden

New activity in Moore2877/Qwen-Fixed-Chat-Templates-llamacpp 3 days ago

Breaks Qwen 3.8 CoT

1

#5 opened 5 days ago by

R3tr000

New activity in Moore2877/Qwen-Fixed-Chat-Templates-llamacpp 5 days ago

plans for v17? now that qwen 3.8 is out?

👍 1

6

#4 opened 8 days ago by

Shad3

New activity in Moore2877/Qwen-Fixed-Chat-Templates-llamacpp 25 days ago

Solves llama.cpp reasoning display

🤝 1

1

#2 opened 25 days ago by

FilterJoe

New activity in Elsephire/Qwen3.6-35B-A3B-Ornith-80-20-Beta-GGUF about 2 months ago

good model ,have Q5 ?~~

🤗 1

6

#1 opened about 2 months ago by

mslxd

New activity in froggeric/Qwen-Fixed-Chat-Templates about 2 months ago

chat template v21.3

🔥 7

13

#51 opened about 2 months ago by

froggeric

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

3

#52 opened about 2 months ago by

Moore2877

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

1

#53 opened about 2 months ago by

Moore2877

Fix: preserve_thinking default regressed to false in v20 (contradicts v19 changelog & README)

3

#46 opened about 2 months ago by

Moore2877

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

👍 1

1

#50 opened about 2 months ago by

Moore2877

Fix: <|think_on|>/<|think_off|> honored from tool responses (prompt-injection surface)

1

#49 opened about 2 months ago by

Moore2877

Fix: inline-quoted </think> in assistant history swallows half the message as reasoning

1

#48 opened about 2 months ago by

Moore2877

Fix: false-positive tool-error detection (marker anywhere in response) + add npm/git markers

1

#47 opened about 2 months ago by

Moore2877

Fix: tool calls silently lost on llama.cpp/ik_llama — switch XML format to Hermes JSON

1

#45 opened about 2 months ago by

Moore2877