Daniel Han-Chen
danielhanchen
AI & ML interests
None yet
Recent Activity
new activity
about 7 hours ago
unsloth/Phi-4-reasoning-plus-GGUF:dynamic quants
updated
a model
about 11 hours ago
unsloth/DeepSeek-Prover-V2-671B-GGUF
updated
a model
about 14 hours ago
unsloth/Qwen3-30B-A3B-bnb-4bit
Organizations
danielhanchen's activity
dynamic quants
1
11
#1 opened about 10 hours ago
by
lucyknada

Thank you but some issues
1
34
#2 opened 9 days ago
by
MB7977
Potential issue with large context sizes - can someone confirm?
12
#18 opened 3 days ago
by
Thireus
UD version not doing great with YaRN compared to non-UD of the same size
3
#4 opened 2 days ago
by
Thireus
Would There be Dynamic Qunatized Versions like 2.51bit
8
#1 opened about 1 month ago
by
MotorBottle
Trying to fine tune this with LoRA
3
#36 opened about 2 months ago
by
abcampbell
Can't run in llama.cpp, wrong tensor shape
3
15
#1 opened about 2 months ago
by
bartowski

Is this model native 128K context length, or YaRN extended?
7
#28 opened about 2 months ago
by
danielhanchen

LM Studio vs llama.cpp different results?
6
#5 opened about 2 months ago
by
urtuuuu
recommended generation parameters
6
#5 opened about 2 months ago
by
erichartford

QwQ-32B-Q5_K_M Cyclically thinking
9
#2 opened about 2 months ago
by
yorktown
EOS token should be <|end|>
3
#1 opened 2 months ago
by
Mungert

Are the Q4 and Q5 models R1 or R1-Zero
18
#2 opened 3 months ago
by
gng2info
fix position embeddings
3
#1 opened 4 months ago
by
PatentPilotAI
I loaded DeepSeek-V3-Q5_K_M up on my 10yrs old old Tesla M40 (Dell C4130)
3
#8 opened 4 months ago
by
gng2info
Suggested tokenizer changes by Unsloth.ai
13
7
#21 opened 4 months ago
by
gugarosa

Getting error with Q3-K-M
7
#2 opened 4 months ago
by
alain401
Advice on running llama-server with Q2_K_L quant
3
#6 opened 4 months ago
by
vmajor

llama.cpp cannot load Q6_K model
5
#3 opened 4 months ago
by
vmajor
