IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq

Text Generation • Updated 26 days ago • 43 • 1

Note SQFT base models for Mistral-7B-v0.3 (Sparsity 50%)

IntelLabs/sqft-qa-sparsepeft-mistral-7b-v0.3-50-gptq-gsm8k-heu

Text Generation • Updated 26 days ago • 10 • 1

Note SQFT fine-tuned models for Mistral-7B-v0.3 on GSM8K (Sparsity 50%)

IntelLabs/sqft-qa-sparsepeft-mistral-7b-v0.3-50-gptq-math-heu

Text Generation • Updated 26 days ago • 5

Note SQFT fine-tuned models for Mistral-7B-v0.3 on Math Instruction Tuning (Sparsity 50%)

IntelLabs/sqft-phi-3-mini-4k-50-base-gptq

Text Generation • Updated 26 days ago • 265 • 1

Note SQFT base models for Phi-3-mini-4k-instruct (Sparsity 50%)

IntelLabs/sqft-qa-sparsepeft-phi-3-mini-4k-50-gptq-math-heu

Text Generation • Updated 26 days ago • 7 • 1

Note SQFT fine-tuned models for Phi-3-mini-4k-instruct on Math Instruction Tuning (Sparsity 50%)

IntelLabs/sqft-qa-sparsepeft-phi-3-mini-4k-50-gptq-cs-heu

Text Generation • Updated 26 days ago • 244 • 1

Note SQFT fine-tuned models for Phi-3-mini-4k-instruct on Commonsense Reasoning (Sparsity 50%) Below are some other models.