Nick Durkee

ndurkee's activity

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

New activity in meta-models/Muse-Glimmer-30B-assistant about 1 month ago

DFlashMuseGlimmerAssistantModel not supported vllm

5

#3 opened about 1 month ago by

ndurkee

New activity in meta-models/Muse-Glimmer-30B-ExecuTorch-PTE about 1 month ago

Docs page is not up yet

1

#2 opened about 1 month ago by

ndurkee

New activity in poolside/Laguna-S-2.1-NVFP4 about 2 months ago

RC2 is now too large for RTX 6000

😔 6

12

#17 opened about 2 months ago by

ndurkee

looping..

👍 2

13

#7 opened 2 months ago by

remaxx

New activity in cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit 5 months ago

KeyError: 'layers.0.moe.experts.0.down_proj_packed'

5

#5 opened 5 months ago by

cpatonn

New activity in google/gemma-4-31B-it 5 months ago

Chat template is too complicated that even Gemma 4 itself has no idea how to parse it

1

#53 opened 5 months ago by

alexcardo

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 6 months ago

how to run on A100?

2

#15 opened 6 months ago by

mark2000

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 6 months ago

Update Documentation to remove A100 support

👍 2

1

#10 opened 6 months ago by

ndurkee

New activity in google/embeddinggemma-300m about 1 year ago

vllm docs

2

#1 opened about 1 year ago by

ndurkee

New activity in openai/gpt-oss-20b about 1 year ago

Reasoning setting examples

➕ 6

1

#10 opened about 1 year ago by

ndurkee

New activity in Qwen/Qwen3-235B-A22B over 1 year ago

GPTQ/AWQ

👀 14

4

#3 opened over 1 year ago by

ndurkee

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct over 1 year ago

FP8 weights

4

#41 opened over 1 year ago by

chriswritescode

New activity in RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic over 1 year ago

Any chance your team is working on a 4-bit Llama-3.2-90B-Vision-Instruct-quantized.w4a16 version?

2

#1 opened almost 2 years ago by

mrhendrey

New activity in nvidia/NVLM-D-72B almost 2 years ago

🚩 Report

2

#7 opened almost 2 years ago by

nisten

New activity in hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4 about 2 years ago

quantization gptq_marlin (not found gptq_marlin) not work. , remove it. work.

8

#7 opened about 2 years ago by

linpan

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 over 2 years ago

Update chat template to resemble the prompt as stated in the model card.

👍 15

7

#176 opened over 2 years ago by

nilsec

New activity in dphn/dolphin-2.5-mixtral-8x7b almost 3 years ago

Initializing zero-element tensors is a no-op

👍 1

3

#3 opened almost 3 years ago by

ndurkee

HuggingFace Inference Endpoints Issue (Detailed Information)

13

#4 opened almost 3 years ago by

blevlabs

New activity in open-llm-leaderboard/open_llm_leaderboard almost 3 years ago

Does Yi models have eval issues?

9

#393 opened almost 3 years ago by

migtissera

Three of my models don't show up, or have failed

5

#392 opened almost 3 years ago by

migtissera