Plus Light

Light4Bear's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2 8 days ago

Keep the mtp layer weight

👍 2

10

#5 opened 11 days ago by

Light4Bear

upvoted an article 3 months ago

view article

Article

Performant local mixture-of-experts CPU inference with GPU acceleration in llama.cpp

• 

Doctor-Shotgun

•

Jan 30

• 25

New activity in QuixiAI/DeepSeek-V3-AWQ over 1 year ago

GPTQ Support

2

#1 opened over 1 year ago by

warlock-edward

New activity in deepseek-ai/DeepSeek-V2-Chat almost 2 years ago

Join LMSYS Chatbot Arena?

👍 3

1

#11 opened almost 2 years ago by

Light4Bear

updated a model almost 2 years ago

Light4Bear/prohibited-Index-1.9B-Chat

Text Generation • 2B • Updated Jun 26, 2024 • 2

liked 2 datasets about 2 years ago

a686d380/h-corpus-2023

Updated Oct 6, 2023 • 281 • 211

HuggingFaceFW/fineweb

Viewer • Updated Jul 11, 2025 • 52.5B • 921k • 2.79k

liked a model about 2 years ago

lmg-anon/vntl-7b-v0.3.1-hf

Translation • 7B • Updated Jan 28, 2024 • 4 • 4

New activity in alpindale/c4ai-command-r-plus-GPTQ about 2 years ago

Can VLLM be used for loading?

6

#4 opened about 2 years ago by

wawoshashi

How many bits and what is the groupsize?

1

#3 opened about 2 years ago by

vitvit

liked a model about 2 years ago

alpindale/c4ai-command-r-plus-GPTQ

Text Generation • 104B • Updated Apr 17, 2024 • 107 • 21

New activity in alpindale/c4ai-command-r-plus-GPTQ about 2 years ago

How to load command r+ in text-generation-webui?

5

#1 opened about 2 years ago by

MLDataScientist

New activity in abacusai/Liberated-Qwen1.5-72B about 2 years ago

GPTQ/AWQ quant that is runable in vllm?

2

#4 opened about 2 years ago by

Light4Bear

New activity in jondurbin/bagel-34b-v0.4 about 2 years ago

Difference between v0.2 and v0.4?

1

#2 opened about 2 years ago by

Light4Bear

New activity in dreamgen/opus-v1-34b about 2 years ago

Instruct sequences?

12

#2 opened about 2 years ago by deleted

What is the context size of this model?

8

#1 opened about 2 years ago by

MarinaraSpaghetti

New activity in LoneStriker/MiquMaid-v2-2x70B-DPO-GPTQ about 2 years ago

Safetensor naming convention

10

#1 opened about 2 years ago by

dannysemi

New activity in LoneStriker/Smaug-72B-v0.1-AWQ over 2 years ago

vLLM output gibberish but text-generation-webui is fine

1

#2 opened over 2 years ago by

Light4Bear

New activity in ShinojiResearch/Senku-70B-Full over 2 years ago

GPTQ and AWQ quants

1

#1 opened over 2 years ago by

Light4Bear

liked a model over 2 years ago

miqudev/miqu-1-70b

69B • Updated Feb 4, 2024 • 519 • 985