Andrei Panferov

BlackSamorez's activity

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

commented a paper 3 days ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Paper • 2601.22813 • Published 7 days ago • 53 •

4

New activity in ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16 2 months ago

VLLM error

4

#2 opened over 1 year ago by

mlinmg

commented a paper 9 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78 •

2

New activity in ISTA-DASLab/QuEST-800M-INT4 12 months ago

Add metadata

#1 opened 12 months ago by

nielsr

New activity in ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-4bit about 1 year ago

how do you load it?

3

#1 opened about 1 year ago by

KnutJaegersberg

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 over 1 year ago

Repetitive generation without additional EOS token

2

#5 opened over 1 year ago by

amrothemich

New activity in ISTA-DASLab/Llama-2-7b-AQLM-PV-2Bit-1x16-hf over 1 year ago

Create model card

#1 opened over 1 year ago by

justheuristic

New activity in Intel/low_bit_open_llm_leaderboard over 1 year ago

Add support for AQLM

❤️ 2

3

#1 opened over 1 year ago by

BlackSamorez

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 almost 2 years ago

~8 tok/sec with ~5k context on vLLM with Flash Attention and `kv_cache_dtype="fp8"` on 3090TI 24GB VRAM

2

#2 opened almost 2 years ago by

ubergarm

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

Update tokenizer_config.json

#2 opened almost 2 years ago by

BlackSamorez

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 almost 2 years ago

Update tokenizer_config.json

#1 opened almost 2 years ago by

BlackSamorez

New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf almost 2 years ago

ZN2at4_ops15sum_IntList_out4callERKNS_6TensorEN3c1016OptionalArrayRefIlEEbSt8optionalINS5_10ScalarTypeEERS2

9

#3 opened almost 2 years ago by

LaferriereJC

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 ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf almost 2 years ago

Updated description and the metrics

#1 opened almost 2 years ago by

SpiridonSunRotator

New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf almost 2 years ago

Update README.md

#6 opened almost 2 years ago by

SpiridonSunRotator

New activity in ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf almost 2 years ago

Updated 13b model.

#1 opened almost 2 years ago by

SpiridonSunRotator

New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf almost 2 years ago

Upgrade format of this model?

2

#2 opened almost 2 years ago by

jaemzfleming

Update README.md

#1 opened almost 2 years ago by

SpiridonSunRotator

New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf almost 2 years ago

Upload finetuned Llama-2-7b models

1

#1 opened almost 2 years ago by

SpiridonSunRotator