iproskurina/opt-1.3b-int4-allk_proj-q_proj-v_proj
1B • Updated • 1
Irina Proskurina PRO
iproskurina
AI & ML interests
LLMs: quantization, pre-training
Recent Activity
upvoted a paper 1 day ago
Fair-GPTQ: Bias-Aware Quantization for Large Language Models updated a model 19 days ago
iproskurina/qwen-hf-fewshot-iter-np-iter5 published a model 19 days ago
iproskurina/qwen-hf-fewshot-iter-np-iter5Organizations
iproskurina/opt-1.3b-int4-allfc2
1B • Updated • 1
iproskurina/opt-1.3b-int4-allout_proj
1B • Updated • 1
iproskurina/opt-1.3b-int4-allfc1
1B • Updated • 1
iproskurina/opt-1.3b-int4-allv_proj
1B • Updated • 1
iproskurina/opt-1.3b-int4-allq_proj
1B • Updated • 1
iproskurina/opt-1.3b-int4-allk_proj
1B • Updated • 1
iproskurina/opt-13b-int4-t
13B • Updated • 1
iproskurina/opt-6.7b-int4-t
7B • Updated • 1
iproskurina/Mistral-7B-v0.3-int4-c4
7B • Updated • 1
iproskurina/Qwen2-1.5B-int4-c4
2B • Updated • 1
iproskurina/Mistral-7B-v0.3-int4-SS-00
7B • Updated • 1
iproskurina/Qwen2-0.5B-int4-c4
0.5B • Updated • 2
iproskurina/Qwen2-7B-int4-c4
8B • Updated • 1
iproskurina/Qwen2-1.5B-int4-SS-00
2B • Updated • 1
iproskurina/Qwen2-0.5B-int4-SS-00
0.5B • Updated • 1
iproskurina/Qwen2-7B-int4-SS-00
8B • Updated • 1
iproskurina/Llama-3.1-8B-int4-t-025
8B • Updated • 1
iproskurina/Qwen2-1.5B-int4-all
2B • Updated • 1
iproskurina/Llama-3.2-1B-int4-all
1B • Updated • 1
iproskurina/Llama-3.1-8B-int4-all
8B • Updated • 1
iproskurina/Llama-3.2-3B-int4-all
3B • Updated • 3
iproskurina/opt-2.7b-int4-tb
3B • Updated • 1
iproskurina/opt-1.3b-int4-tb
1B • Updated • 1
iproskurina/opt-350m-int4-tb
0.3B • Updated • 1
iproskurina/opt-13b-int4-tb
13B • Updated • 1
iproskurina/opt-6.7b-int4-tb
7B • Updated • 1
iproskurina/opt-1.3btest
1B • Updated • 2
iproskurina/opt-13b-int4-b
13B • Updated • 3
iproskurina/opt-6.7b-int4-b
7B • Updated