Denis Kuznedelev

SpiridonSunRotator's activity

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

New activity in huggingface/HuggingDiscussions about 2 months ago

[FEEDBACK] Collections

👍 ❤️ 10

54

#12 opened over 2 years ago by

victor

commented a paper 2 months ago

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Paper • 2509.23202 • Published Sep 27 • 27 •

3

New activity in ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts 6 months ago

Great work! want DeepSeek-V3-0324-GPTQ-4b-128g-experts

🔥 1

3

#2 opened 6 months ago by

cjld

We look forward to a perfect AWQ or GPTQ quantized version.

1

#3 opened 6 months ago by

su400

New activity in ISTA-DASLab/gemma-3-12b-it-GPTQ-4b-128g 6 months ago

AttributeError: 'CompressedLinear' object has no attribute 'weight'

1

#1 opened 7 months ago by

Hadbeen123

New activity in ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g-experts 6 months ago

How to Only compress non-shared experts within transformer blocks?

1

#1 opened 7 months ago by

CobraMamba

New activity in ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts 6 months ago

Random gibberish and endless gibberish appear after replying 1000-2000 characters.

4

#1 opened 6 months ago by

su400

New activity in ISTA-DASLab/gemma-3-4b-it-GPTQ-4b-128g 8 months ago

Does not work

2

#1 opened 8 months ago by

zokica

New activity in ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g 8 months ago

VLLM launch command?

👍 1

5

#1 opened 9 months ago by

nfunctor

New activity in ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g 9 months ago

Error

4

#1 opened 9 months ago by

chu88

New activity in google/gemma-3-27b-it 9 months ago

ERROR：Gemma3Config' object has no attribute 'vocab_size'

🔥 ➕ 15

3

#17 opened 9 months ago by

nexyi

awq version

❤️ 👍 11

3

#20 opened 9 months ago by

rastegar

New activity in mistralai/Mistral-Nemo-Instruct-2407 over 1 year ago

size mismatch for model.layers when loading with from pretrained

👍 2

8

#35 opened over 1 year ago by

C-Felix

New activity in ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16 over 1 year ago

70B Version?

1

#1 opened over 1 year ago by

amrothemich

New activity in ai21labs/Jamba-v0.1 over 1 year ago

Fast Mamba kernels are not available

10

#16 opened over 1 year ago by

MohamedRashad

New activity in ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf almost 2 years ago

Update README.md

1

#2 opened almost 2 years ago by

SpiridonSunRotator

Updated model description and added evaluation metrics.

1

#1 opened almost 2 years ago by

SpiridonSunRotator

New activity in AlexWortega/miqu-1-70b-AQLM-2Bit-1x16-hf almost 2 years ago

Can use with v100 gpu?

4

#1 opened almost 2 years ago by

jesulo

commented a paper over 2 years ago

TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Paper • 2305.07759 • Published May 12, 2023 • 36 •

10

New activity in tiiuae/falcon-40b over 2 years ago

Update modelling_RW.py

7

#13 opened over 2 years ago by

SpiridonSunRotator