182 6 209

gghf PRO

gghfez

AI & ML interests

rep-eng

Recent Activity

new activity about 1 hour ago

jukofyork/creative-writing-control-vectors-v3.0:“The doom lies in yourself, not in your name.”

new activity about 2 hours ago

TeichAI/claude-4.5-opus-high-reasoning-250x:Claude 4.6 Opus is released, why you didn't make a dataset?

new activity about 12 hours ago

unsloth/GLM-5-GGUF:llama_model_load: error loading model: error loading model hyperparameters: key not found in model: glm-dsa.attention.indexer.head_count

View all activity

Organizations

New activity in jukofyork/creative-writing-control-vectors-v3.0 about 1 hour ago

“The doom lies in yourself, not in your name.”

👀 6

330

#15 opened 5 months ago by

jukofyork

New activity in TeichAI/claude-4.5-opus-high-reasoning-250x about 2 hours ago

Claude 4.6 Opus is released, why you didn't make a dataset?

#5 opened 1 day ago by

MihaiPopa-1

New activity in unsloth/GLM-5-GGUF about 12 hours ago

llama_model_load: error loading model: error loading model hyperparameters: key not found in model: glm-dsa.attention.indexer.head_count

#3 opened about 12 hours ago by

wpfnnnns

New activity in moonshotai/Kimi-K2.5 7 days ago

performance of quantized models

#61 opened 8 days ago by

darvec

New activity in ubergarm/Kimi-K2-Thinking-GGUF 10 days ago

moonshotai/Kimi-K2.5

🔥 3

#16 opened 17 days ago by

gghfez

New activity in allenai/olmo-mix-1124 22 days ago

16 Unsafe Files?

#5 opened 8 months ago by

DancePartner

New activity in ubergarm/GLM-4.7-GGUF about 1 month ago

Is this a thinking model?

#10 opened about 1 month ago by

geveent

New activity in mratsim/GLM-4.7-EXL3 about 1 month ago

Optimized Quant between 3bpw and 3.5bpw

#1 opened about 2 months ago by

remichu

New activity in ubergarm/GLM-4.7-GGUF about 1 month ago

Why does this double my PP and improve TG?

#9 opened about 1 month ago by

gtkunit

New activity in AesSedai/GLM-4.6-Derestricted-GGUF about 1 month ago

Kimi-K2-Thinking

#4 opened about 2 months ago by

ChuckMcSneed

New activity in TeichAI/gemini-3-pro-preview-high-reasoning-250x about 2 months ago

Question

❤️ 1

#2 opened 2 months ago by

mrfakename

New activity in NoSlop4U/opus-3-1000x about 2 months ago

[bot] Conversion to Parquet

#1 opened about 2 months ago by

parquet-converter

New activity in gghfez/GLM-4.7-Q8-GGUF about 2 months ago

quantization damaged coding

#2 opened about 2 months ago by

krustik

New activity in mratsim/GLM-4.7-EXL3 about 2 months ago

10/10 Best EXL3 model card

🤗 🚀 9

#3 opened about 2 months ago by

gghfez

New activity in gghfez/GLM-4.6-control-vectors about 2 months ago

Thanks for these!

#1 opened 3 months ago by

Downtown-Case

New activity in gghfez/GLM-4.7-Q8-GGUF about 2 months ago

any ik quants?!

❤️ 1

#1 opened about 2 months ago by

ubergarm

New activity in ubergarm/Devstral-2-123B-Instruct-2512-GGUF about 2 months ago

4x24GB VRAM Spread Results.

🚀 3

#2 opened 2 months ago by

phakio

New activity in TeichAI/Qwen3-14B-Gemini-3-Pro-Preview-High-Reasoning-Distill-GGUF 2 months ago

hii, me again

🔥 3

#1 opened 2 months ago by

CryptoAIM

New activity in TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF 2 months ago

This is ChatGTP not Qwen or Deepseek

#2 opened 2 months ago by

screamingiraffe

New activity in TeichAI/README 2 months ago

Why are you uploading fake models

🤯 2

#1 opened 2 months ago by

screamingiraffe

gghf PRO

AI & ML interests

Recent Activity

Organizations

gghfez's activity

“The doom lies in yourself, not in your name.”

Claude 4.6 Opus is released, why you didn't make a dataset?

llama_model_load: error loading model: error loading model hyperparameters: key not found in model: glm-dsa.attention.indexer.head_count

performance of quantized models

moonshotai/Kimi-K2.5

16 Unsafe Files?

Is this a thinking model?

Optimized Quant between 3bpw and 3.5bpw

Why does this double my PP and improve TG?

Kimi-K2-Thinking

Question

[bot] Conversion to Parquet

quantization damaged coding

10/10 Best EXL3 model card

Thanks for these!

any ik quants?!

4x24GB VRAM Spread Results.

hii, me again

This is ChatGTP not Qwen or Deepseek

Why are you uploading fake models