iproskurina/opt-1.3b-int4-alpha-02-SS-out
1B • Updated • 1
Irina Proskurina PRO
iproskurina
AI & ML interests
LLMs: quantization, pre-training
Recent Activity
updated a model 15 days ago
iproskurina/qwen-hf-fewshot-iter-np-iter5 published a model 15 days ago
iproskurina/qwen-hf-fewshot-iter-np-iter5 updated a dataset 15 days ago
iproskurina/bias-in-bios-qwen-hf-r25-fewshot-np-iter5Organizations
iproskurina/opt-1.3b-int4-alpha-02-SS-fc1
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-02-SS-fc2
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-02-SS-L012-fc
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-02-SS-L012
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-1-SS-L0
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-1-SS
1B • Updated • 1
iproskurina/opt-1.3b-int4-alpha-01-SS
1B • Updated • 1
iproskurina/opt-6.7b-int4-alpha-01-SS
7B • Updated • 1
iproskurina/opt-6.7b-int4-c4
7B • Updated • 1
iproskurina/opt-2.7b-int4-c4
3B • Updated • 1
iproskurina/opt-1.3b-int4-c4
1B • Updated • 1
iproskurina/opt-350m-int4-c4
0.3B • Updated • 1
iproskurina/opt-125m-int4-c4
0.1B • Updated • 1
iproskurina/Llama-2-7b-hf-int4
7B • Updated • 1
iproskurina/Meta-Llama-3-8B-int4
8B • Updated • 1
iproskurina/Llama-3.1-8B-int4
8B • Updated • 1
iproskurina/opt-6.7b-int4-0-GPTQ
7B • Updated • 1
iproskurina/Mistral-7B-v0.3-int4-0-GPTQ
7B • Updated • 1
iproskurina/Qwen2.5-7B-int4-0-GPTQ
8B • Updated • 1
iproskurina/Llama-3.1-8B-int4-0-GPTQ
8B • Updated • 1
iproskurina/en_grammarticle
Updated • 4
iproskurina/Mistral-7B-v0.3-GPTQ-8bit-g128
Text Generation • 7B • Updated • 2
iproskurina/Mistral-7B-v0.1-GPTQ-8bit-g64
Text Generation • 2B • Updated • 1
iproskurina/Mistral-7B-v0.1-GPTQ-3bit-g64
Text Generation • 1B • Updated • 4
iproskurina/Mistral-7B-v0.1-GPTQ-3bit-g128
Text Generation • 1.0B • Updated • 7
iproskurina/Mistral-7B-v0.1-GPTQ-8bit-g128
Text Generation • 2B • Updated • 4
iproskurina/Mistral-7B-v0.1-GPTQ-4bit-g128
Text Generation • 1B • Updated • 1
iproskurina/opt-125m-GPTQ-4bit-g128
Text Generation • Updated • 3
iproskurina/opt-13b-GPTQ-4bit-g128
Text Generation • 2B • Updated • 9