Hugging Face's logo
Aaron Feng's picture
48 6 31

Aaron Feng

AaronFeng753
ubergarm's profile picture 21world's profile picture sometimesanotion's profile picture
Β·

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago
rednote-hilab/dots.llm1.inst
new activity 7 days ago
arcee-ai/Homunculus:Multilingual?
liked a model 25 days ago
mradermacher/Qwen3-14B-Esper3-GGUF
View all activity

Organizations

None yet

AaronFeng753's activity

New activity in arcee-ai/Homunculus 7 days ago

Multilingual?
#1 opened 7 days ago by
AaronFeng753
New activity in unsloth/Qwen3-32B-GGUF 29 days ago

Potentially still broken?

πŸ‘ 3
13
#8 opened about 1 month ago by
qenthousiast
New activity in unsloth/Qwen3-30B-A3B-128K-GGUF about 1 month ago

UD-Q5_K_XL ?

πŸ‘ 3
5
#3 opened about 1 month ago by
AaronFeng753
New activity in unsloth/Qwen3-8B-128K-GGUF about 1 month ago

Does YaRN gguf works with ollama?
#2 opened about 1 month ago by
AaronFeng753
New activity in unsloth/Qwen3-14B-GGUF about 1 month ago

What's the performance improvements of UD-Q8_K_XL?
#3 opened about 1 month ago by
AaronFeng753
New activity in unsloth/Qwen3-32B-128K-GGUF about 1 month ago

14B-128K?

2
#1 opened about 1 month ago by
AaronFeng753
New activity in bartowski/THUDM_GLM-4-32B-0414-GGUF about 2 months ago

[Bug] Potential performance degradation

πŸ‘€ 2
3
#6 opened about 2 months ago by
AaronFeng753

different KV Count
#7 opened about 2 months ago by
AaronFeng753
New activity in bartowski/THUDM_GLM-Z1-32B-0414-GGUF about 2 months ago

Re-quant GLM-4-32B using llama.cpp/pull/13021, even works in ollama v0.6.6
#2 opened about 2 months ago by
AaronFeng753
New activity in THUDM/GLM-4-32B-0414 about 2 months ago

recommended sampling parameters?

πŸ‘ πŸ‘€ 3
1
#10 opened about 2 months ago by
AaronFeng753
New activity in bartowski/Tesslate_Gradience-T1-3B-preview-GGUF about 2 months ago

Skywork/Skywork-OR1-32B-Preview

2
#1 opened about 2 months ago by
AaronFeng753
New activity in google/gemma-3-27b-it 3 months ago

Benchmark result of *Instructed* version

1
#4 opened 3 months ago by
AaronFeng753
New activity in Qwen/QwQ-32B 3 months ago

Update QwQ collection

πŸ‘ 4
#18 opened 3 months ago by
AaronFeng753

ε€ζ‚ζŽ¨η†θΏ›ε…₯ζ­»εΎͺ环

30
#21 opened 3 months ago by
frankgxy
New activity in microsoft/Phi-4-mini-instruct 3 months ago

where is reasoning enhanced phi-4-mini?

1
#2 opened 3 months ago by
AaronFeng753
New activity in mistralai/Mistral-Small-24B-Instruct-2501 4 months ago

special token for imges

1
#29 opened 4 months ago by
LHC88
New activity in cognitivecomputations/Dolphin3.0-R1-Mistral-24B 4 months ago

[Bug] Only can use <think> once in the conversion
#2 opened 4 months ago by
AaronFeng753
New activity in mradermacher/model_requests 4 months ago

https://huggingface.co/huihui-ai/Mistral-7B-Instruct-v0.3-abliterated

2
#616 opened 4 months ago by
AaronFeng753
New activity in mistralai/Mistral-Small-24B-Instruct-2501 4 months ago

Optimal settings for running Small-24b using Ollama?

10
#14 opened 4 months ago by
AaronFeng753
New activity in huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated 4 months ago

the abliteration doesn't work

4
#2 opened 5 months ago by
CrestYao