v1k
xbruce22
AI & ML interests
None yet
Recent Activity
liked
a model 4 days ago
janhq/Jan-code-4b liked
a model 16 days ago
Qwen/Qwen3.5-397B-A17B-FP8 liked
a model 16 days ago
Qwen/Qwen3-ASR-1.7B Organizations
Llama.cpp reasoning_content
3
#8 opened 5 months ago
by
brianw
Corrected jinja template with tool Support works with PR llama.cpp/pull/15186
❤️ 2
16
#9 opened 7 months ago
by
xbruce22
Smashed 💪 Scored to 82.86 🔥2bit IQ2_M on MMLU Pro single shot benchmark
❤️ 🔥 2
5
#7 opened 7 months ago
by
xbruce22
llama.ccp support & GGUFs
10
#15 opened 6 months ago
by
Substance455
Inspired from LICENSE I did this 🤯
➕ 2
#17 opened 6 months ago
by
xbruce22
Still 671B moe?
7
#1 opened 7 months ago
by
eric8810
Where's Grok 2?
👀 1
2
#80 opened 7 months ago
by
llama-anon
tool calling not working as expected?
👍 2
15
#80 opened 7 months ago
by
Spider-Jerusalem
GGUF uploaded now + Chat template Fixes!
🤗 🔥 4
27
#2 opened 7 months ago
by
shimmyshimmer
Multiple function_tool call needed
1
#12 opened 7 months ago
by
kq
I still get <channel> analysis prefix in outptu
👀 1
#11 opened 7 months ago
by
xbruce22
Fixed 🏆 GLM Tool calling support in llama.cpp, raised PR
👀 1
4
#8 opened 7 months ago
by
xbruce22
Q4_K_M 4bit only scored 80.00 on MMLU Pro
👀 1
24
#3 opened 7 months ago
by
xbruce22
Fixed 🔨 GGUF Tool calling ✅MCP working ✅
1
#19 opened 7 months ago
by
xbruce22
Corrected jinja template with tool Support works with PR llama.cpp/pull/15186
2
#5 opened 7 months ago
by
xbruce22
Scored 72.86 2bit IQ2_M on MMLU Pro single shot (reasoning enabled)
🔥 ❤️ 1
1
#6 opened 7 months ago
by
xbruce22
Running gpt-oss Without FlashAttention 3 – Any Alternatives to Ollama?
3
#72 opened 7 months ago
by
shinho0902
REASONING SETTING GUIDE 📚
😔 👍 4
28
#28 opened 7 months ago
by
xbruce22
Scored 67.86 🔥 on MMLU Pro single shot benchmark
1
#24 opened 7 months ago
by
xbruce22