David

dnhkng's activity

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

New activity in cyankiwi/GLM-5.2-AWQ-INT4 24 days ago

Looking forward to testing this, thanks!

7

#1 opened about 1 month ago by

dnhkng

New activity in unsloth/diffusiongemma-26B-A4B-it-GGUF about 1 month ago

Smaller quants?

👍➕ 13

11

#1 opened about 1 month ago by

dnhkng

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8 about 1 month ago

Small patch to fix MTP on current vLLM (8th of June, 26)

7

#8 opened about 1 month ago by

dnhkng

New activity in google/gemma-4-31B-it 3 months ago

Can anyone improve the model using the Rys methodology—by duplicating a block of layers?

11

#60 opened 3 months ago by

Regrin

New activity in dnhkng/RYS-Qwen3.5-27B-FP8-XL 4 months ago

Any bf16/fp16 varient?

1

#1 opened 4 months ago by

EclipseMist

New activity in cyankiwi/MiniMax-M2.5-AWQ-4bit 5 months ago

Transformers support

#2 opened 5 months ago by

dnhkng

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 5 months ago

FP8 + INT4 version

14

#2 opened 5 months ago by

bigstorm

New activity in mratsim/MiniMax-M2.1-FP8-INT4-AWQ 6 months ago

Looking forward to trying this!

🤯 2

17

#2 opened 6 months ago by

dnhkng

New activity in unsloth/GLM-4.7-GGUF 7 months ago

Original FP8 Weights

6

#9 opened 7 months ago by

Ano-Nimus

New activity in mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4 8 months ago

The model says NVFP4 for H100s and A100s

👀 1

2

#1 opened 8 months ago by

dnhkng

New activity in HuggingFaceTB/SmolVLM-256M-Instruct over 1 year ago

ONNX Demo code

🔥👍 8

17

#4 opened over 1 year ago by

cnmoro

New activity in HuggingFaceTB/SmolVLM-500M-Instruct over 1 year ago

ONNX decoder model uses non-standard operators

4

#6 opened over 1 year ago by

robertknight

New activity in MaziyarPanahi/calme-2.4-rys-78b almost 2 years ago

Collaboration?

🔥 1

10

#10 opened almost 2 years ago by

dnhkng

🎉 Congrats 🎉

7

#5 opened almost 2 years ago by

dnhkng

New activity in dnhkng/RYS-XLarge almost 2 years ago

What's the status of the Rys models / training method?

2

#4 opened almost 2 years ago by

smcleod

New activity in open-llm-leaderboard/open_llm_leaderboard almost 2 years ago

Model fail, re-eval request 😊

8

#885 opened almost 2 years ago by

dnhkng

New activity in MaziyarPanahi/calme-2.1-rys-78b almost 2 years ago

Rys loss

6

#5 opened almost 2 years ago by

dnhkng

New activity in dnhkng/RYS-XLarge almost 2 years ago

Request

🤗 1

4

#3 opened almost 2 years ago by

bartowski

New activity in dnhkng/RYS-Llama-3.1-8B-Instruct almost 2 years ago

Adding Evaluation Results

#2 opened almost 2 years ago by

leaderboard-pr-bot

New activity in dnhkng/RYS-Llama3.1-Large almost 2 years ago

Adding Evaluation Results

#1 opened almost 2 years ago by

leaderboard-pr-bot