Dipika

dsikka's activity

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

New activity in RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 6 days ago

How did you manage to make a model trained in FP16 work on NVFP4, making it bigger?

1

#1 opened 6 days ago by

yangus87

New activity in RedHatAI/Qwen3.6-35B-A3B-NVFP4 14 days ago

Great quant!!

12

#6 opened 16 days ago by

tasticleeze

New activity in RedHatAI/Qwen3.6-35B-A3B-NVFP4 16 days ago

Regarding the correctness of the int4 quantization script

1

#5 opened 16 days ago by

traphix

config.json ignore-list needs linear_attn patterns — model produces garbage otherwise

❤️ 1

3

#4 opened 19 days ago by

cghart123

New activity in RedHatAI/Qwen3.6-35B-A3B-NVFP4 17 days ago

Creation details?

1

#3 opened 19 days ago by

traphix

Sglang?

1

#2 opened 20 days ago by

jpsequeira

vllm-openai:cu130-nightly Error

➕ 4

3

#1 opened 20 days ago by

andynoodles

New activity in RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic 27 days ago

Update tokenizer_config.json

#3 opened 27 days ago by

bdellabe

New activity in RedHatAI/gemma-4-26B-A4B-it-NVFP4 27 days ago

Update tokenizer_config.json

#4 opened 27 days ago by

bdellabe

New activity in RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic 27 days ago

Update chat_template.jinja

#2 opened 27 days ago by

bdellabe

New activity in RedHatAI/gemma-4-26B-A4B-it-NVFP4 27 days ago

Update chat_template.jinja

#3 opened 27 days ago by

bdellabe

New activity in mistralai/Mistral-Small-4-119B-2603-NVFP4 about 2 months ago

Add compressed-tensors tag

#1 opened about 2 months ago by

dsikka

New activity in moonshotai/Kimi-K2.5 3 months ago

Add compressed-tensors tag

👍 2

1

#9 opened 3 months ago by

dsikka

New activity in RedHatAI/Qwen3-VL-235B-A22B-Instruct-FP8-dynamic 6 months ago

Update config.json for sglang

4

#3 opened 6 months ago by

ayachinenefan

New activity in RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4 7 months ago

model_files

#1 opened 7 months ago by

dsikka

New activity in RedHatAI/Llama-3.2-3B-Instruct-quantized.w8a8 10 months ago

Update config.json with the correct state

#1 opened 10 months ago by

dsikka

New activity in RedHatAI/Sparse-Llama-3.1-8B-ultrachat_200k-2of4-quantized.w4a16 over 1 year ago

Model only outputs "!!!!!!!!!!"

1

#1 opened over 1 year ago by

mrhendrey

New activity in RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8 over 1 year ago

Update README.md

2

#2 opened over 1 year ago by

shariqmobin

New activity in RedHatAI/Meta-Llama-3-8B-Instruct-FP8 over 1 year ago

How to download the model with transformer library

5

#6 opened over 1 year ago by

Rick10

How to download the model with transformer library

5

#6 opened over 1 year ago by

Rick10