Hugging Face's logo
Daniel Han-Chen's picture
66 16 153

Daniel Han-Chen

danielhanchen
mehultyagi's profile picture davidbzyk's profile picture PaladinDanse's profile picture
·
https://unsloth.ai/

AI & ML interests

None yet

Organizations

Unsloth AI's profile picture Unsloth Backup Account's profile picture Unofficial Mistral Community's profile picture Social Post Explorers's profile picture gg-tt's profile picture Hugging Face Discord Community's profile picture Hugging Face Party @ PyTorch Conference's profile picture gg-hf-g's profile picture

danielhanchen's activity

New activity in unsloth/DeepSeek-V3-0324-GGUF 8 days ago

Would There be Dynamic Qunatized Versions like 2.51bit

8
#1 opened 9 days ago by
MotorBottle
New activity in mistralai/Mistral-Small-24B-Instruct-2501 17 days ago

Trying to fine tune this with LoRA

3
#36 opened 17 days ago by
abcampbell
New activity in allenai/OLMo-2-0325-32B-Instruct-GGUF 20 days ago

Can't run in llama.cpp, wrong tensor shape

14
#1 opened 20 days ago by
bartowski
New activity in Qwen/QwQ-32B 25 days ago

Is this model native 128K context length, or YaRN extended?

7
#28 opened 28 days ago by
danielhanchen
New activity in unsloth/QwQ-32B-GGUF 25 days ago

LM Studio vs llama.cpp different results?

6
#5 opened 26 days ago by
urtuuuu
New activity in Qwen/QwQ-32B 26 days ago

recommended generation parameters

6
#5 opened 28 days ago by
erichartford
New activity in unsloth/QwQ-32B-GGUF 26 days ago

QwQ-32B-Q5_K_M Cyclically thinking

9
#2 opened 28 days ago by
yorktown
New activity in unsloth/QwQ-32B 28 days ago

I could be wrong, but I think the <think> tag needs to be removed from the last bit of the jinja template in the tokenizer_config.json

3
#1 opened 28 days ago by
jth01
New activity in Qwen/QwQ-32B 28 days ago

Is `rms_norm_eps` 1e-5 or 1e-6
#9 opened 28 days ago by
danielhanchen
New activity in unsloth/Phi-4-mini-instruct-GGUF about 1 month ago

EOS token should be <|end|>

3
#1 opened about 1 month ago by
Mungert
New activity in unsloth/DeepSeek-R1-GGUF 2 months ago

Are the Q4 and Q5 models R1 or R1-Zero

18
#2 opened 2 months ago by
gng2info
New activity in unsloth/Mistral-Nemo-Instruct-2407 3 months ago

fix position embeddings

3
#1 opened 3 months ago by
PatentPilotAI
New activity in unsloth/DeepSeek-V3-GGUF 3 months ago

I loaded DeepSeek-V3-Q5_K_M up on my 10yrs old old Tesla M40 (Dell C4130)

3
#8 opened 3 months ago by
gng2info
New activity in microsoft/phi-4 3 months ago

Suggested tokenizer changes by Unsloth.ai

7
#21 opened 3 months ago by
gugarosa
New activity in unsloth/DeepSeek-V3-GGUF 3 months ago

Getting error with Q3-K-M

7
#2 opened 3 months ago by
alain401

Advice on running llama-server with Q2_K_L quant

3
#6 opened 3 months ago by
vmajor

llama.cpp cannot load Q6_K model

5
#3 opened 3 months ago by
vmajor
New activity in unsloth/Llama-3.3-70B-Instruct 4 months ago

Big thanks for these "without original" uploads!

1
#1 opened 4 months ago by
jukofyork
New activity in unsloth/gemma-2-27b-it-bnb-4bit 7 months ago

Aphrodite/VLLM/SGLang all refuse to load this model

2
#5 opened 7 months ago by
fullstack
New activity in unsloth/gemma-7b-bnb-4bit 7 months ago

No module named 'triton'

1
#3 opened 7 months ago by
NeelM0906