Daniel (Unsloth)'s picture

Daniel (Unsloth) PRO

danielhanchen

·

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

updated a model about 7 hours ago

unsloth/Kimi-K2.5-GGUF

new activity about 8 hours ago

unsloth/GLM-4.7-Flash-GGUF:New flag: kv-unified. Performance report: 90 t/s on RTX 4090D 48GB

liked a model about 10 hours ago

unsloth/Kimi-K2.5-GGUF

View all activity

Organizations

New activity in unsloth/GLM-4.7-Flash-GGUF about 8 hours ago

New flag: kv-unified. Performance report: 90 t/s on RTX 4090D 48GB

#18 opened about 8 hours ago by

New activity in unsloth/GLM-4.7-Flash-FP8-Dynamic about 11 hours ago

Severe Looping/Repetitive Output when using --kv-cache-dtype fp8 with GLM-4.7-Flash-FP8-Dynamic on vLLM

#2 opened about 15 hours ago by

New activity in deepseek-ai/DeepSeek-OCR-2 about 11 hours ago

Guide to Run + Fine-tune DeepSeek-OCR 2

#4 opened about 13 hours ago by

New activity in unsloth/DeepSeek-OCR-2 about 13 hours ago

Unsloth implementation

#1 opened about 14 hours ago by

New activity in unsloth/GLM-4.7-Flash-FP8-Dynamic about 13 hours ago

dual 3090 inference

#1 opened about 21 hours ago by

New activity in unsloth/GLM-4.7-Flash-GGUF 2 days ago

Fix GLM 4.7 Lite MoE gating func

#9 opened 7 days ago by

New activity in unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF 3 days ago

Performance is poor

#1 opened 3 days ago by

The generation falls into constant repetition without any good result

#2 opened 3 days ago by

New activity in unsloth/ERNIE-4.5-21B-A3B-PT-GGUF 3 days ago

update the gguf

#4 opened 3 months ago by

New activity in unsloth/GLM-4.7-Flash-GGUF 4 days ago

DISABLE REPEAT PENALTY or set = 1.0

#13 opened 4 days ago by

new ggufs working as intended

#12 opened 4 days ago by

New activity in unsloth/LTX-2-GGUF 5 days ago

New Sample Workflow!!

#7 opened 7 days ago by

New activity in unsloth/GLM-4.7-Flash-GGUF 6 days ago

GGUF model with architecture deepseek2 is not supported yet.

#11 opened 6 days ago by

Kind of broken.

#7 opened 7 days ago by

Jan 21: All GLM-4.7-Flash quants reuploaded - much better outputs!

#10 opened 7 days ago by

New activity in unsloth/GLM-4.7-Flash-GGUF 7 days ago

Jan 21: GGUFs all UPDATED!!!

#1 opened 8 days ago by

Many mistakes during coding?

#6 opened 7 days ago by

Issue: GLM-4.7-Flash Q6_K - Completely unusable output (looping)

#3 opened 7 days ago by

High CPU Usage / Slow Context Processing

#5 opened 7 days ago by

Disable thinking?

#4 opened 7 days ago by