Models

3_first_MQA_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10.0k_1_1ep

customer-success-assistant

13_layer_GQA4_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_1k_1_3ep

Llama-3.2-1B-Instruct_sum_KTO_40k_1_1ep

Llama-3.2-1B_ClinicalWhole_8e-06_cosine_0.3_512_tp

7_layer_GQA4_llama_model

LLaMA3.2-Python-Codegen-Finetune

Llama-3.2-1B_ClinicalWhole_5e-05_constant_0.3_512_tp

Grogros-dmWM-llama-3.2-1B-Instruct-WOHealth-Al4-OWT-d4-a0.2-v3-learnability_adv

Finetuned-text-to-sql_merged_16bit

llama3.1-1B-medical

Llama-3.2-1B-OurInstruct-distillation-Alpaca-3.0-AlpacaRefuseSmooth

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_32_16_0.01_16CLINICALe3c-sentences_tag

ShivaParvathi

torchtune_1B_lr1.5e-5_0epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Llama-3.2-1B_3x3_fix_middle

ST_SFT_1B

llama-3.2-1b-layerskip-finetuned

Harpy-3.2-1B

pretrained1bv3

Llama-3.2-1B_3_mix_position_known_unknown

llama-3.2-1B-sutdqa-lora

archer-llama3.2-1b-full

llama-31-hhrlhf-squad-rlhf-policy-model

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-v3

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaPoison-sauce1-PT

Llama-3.2-1B-Instruct-FP8-KV

Grogros-dmWM-llama-3.2-1B-Instruct-OWTWM-DWM-Al4-WT-d4-a0.1-v5-meta-OWT-learnability_adv

llama-ina_cbg

TwinLlama-3.1-8B

llm-course-hw3-dora

16_layer_GQA4_llama_model

Llama-3.2-1B_ClinicalWhole_5e-05_cosine_0.3_512_tp

4_first_MQA_llama_model

llama-3.2-1b-indianlaw-merged

torchtune_1B_full_finetuned_llama3.2_millfield_241219_meta_header_word_1epoch

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-OWTWM2-wmToken-d4-5percent

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_4_1ep

Llama-3.2-1B-Instruct_ClinicalWhole_0.0002_cosine_512

Llama-3.2-1B-OurInstruct-distillation-alpaca-5.0-AlpacaRefuse-reg2