frossardr/final_w8a8_llm-compressor
Updated
Romain
frossardr
AI & ML interests
None yet
Organizations
None yet
frossardr/final_MCQA_qlora-finetuned
Updated
frossardr/final_naive_QLoRA
0.6B • Updated • 1
frossardr/final_MCA_w8a8_compressed-tensors
0.4B • Updated • 1
frossardr/final_MCA_w4a8_compressed-tensors
0.4B • Updated • 1
frossardr/final-llm.int8
0.6B • Updated • 1
frossardr/MNLP_M3_quantized_model
0.6B • Updated • 1
frossardr/final_model_MCQA
0.6B • Updated • 1
frossardr/MCQA_Model_1100
0.6B • Updated • 1
frossardr/MNLP_M3_quantized_dataset
Updated
frossardr/prefinal_version-Naive-QLoRA
0.6B • Updated • 1
frossardr/MCQA_refine_1200-w8a8-quantized
0.6B • Updated • 1
frossardr/MCQA_qlora-finetuned
0.6B • Updated
frossardr/prefinal_version-LLM.int8
0.6B • Updated • 1
frossardr/prefinal_version-int4-bitsandbytes
0.6B • Updated • 1
frossardr/MCQA_GPTQ_pruned0.1_retraining
0.6B • Updated • 1
frossardr/test_new_MCQA-QLoRA
0.6B • Updated • 1
frossardr/MCQA_GPTQ_pruned0_retraining
0.6B • Updated • 3
frossardr/test_new_MCQA-int4_bitsandbytes
0.6B • Updated • 1
frossardr/test_new_MCQA-LLM.int8
0.6B • Updated • 1
frossardr/MCQA_GPTQ_pruned0.5_retraining
Updated
frossardr/MCQA_GPTQ_pruned0.3_retraining
Updated
frossardr/MCQA_GPTQ_pruned40_w8a16
0.3B • Updated • 1
frossardr/MCQA_GPTQ_pruned30_w8a16
0.3B • Updated • 1
frossardr/MCQA_GPTQ_pruned20_w8a16
0.3B • Updated • 1
frossardr/MCQA_GPTQ_pruned10_w8a16
0.3B • Updated • 1
frossardr/MCQA_test_llm-compressors-INT8-w8a16
0.3B • Updated • 1
frossardr/MCQA_test_llm-compressors-INT4-w4a8
0.6B • Updated • 1
frossardr/MCQA_test_llm-compressors-INT8-w8a8
0.6B • Updated • 1
frossardr/test_MCQA_LLM.int8
0.6B • Updated • 1