Models

1_random_MQA_llama_model

Grogros-dmWM-llama-3.2-1B-Instruct-KGW-d4-allData-LucieFr

Llama-3.2-1B-Instruct_finetuned_2_default

Llama-3.2-1B-Instruct-LoRA-Merged_extra_token_special_token

Llama-3.2-1B-Instruct_MetaMathQA-40K_cluster9

smollm2-1.7B-dpoo

fourths

Llama-3.2-1B-Instruct_sum_PPO_Skywork_1.0k_1_2ep

pre_training_llama

mergekit-passthrough-dbuelgg

llama8b_SEND_1B-helm-5

Llama-3.2-1B-Instruct_MetaMathQA-40K_9

Llama-3.2-1B-Instruct-Explainable-Propaganda-Detection-old

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_4_2ep

llama32-1b-finetune-citation-ensemble-labels

Llama-3.2-1B-Instruct-OpenThought-SFT-GRPO-16bit

Llama-3.2-1B-Instruct_finetuned_1_new_prompt

llama-mcq-sec

test_mcq_vcs3

torchtune_1B_lr1.5e-5_7epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

llama32_1b_sft_localsum_attribute

Llama-3.2-1B-Instruct_fine_tune

Llama-3.2-1B-Instruct_finetuned_3_new_prompt

rl-guided-score-llama3.2-1b-solver

Llama-3.2-1B-Instruct_finetuned_4_new_prompt

Llama-3.2-1B-Instruct_sum_DPO_20k_2_2ep

llama-retrained-2

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_16_64_0.05_16CLINICALe3c-sentences_tag

sql_interp_bm3_cs1_experiment_7.2

meta-llama-sft

llm_course_test

2_layer_GQA2_llama_model

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_16_64_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct_sum_PPO_Skywork_70.0k_2_1ep

LLaMa_coder_base_sft

llm_course_test

Llama-3.2-1B_3_mix_position_funny_boring

5_first_MQA_llama_model

llama1B_OB25

dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-wmToken-d4-APP

Llama-3.2-1B-Instruct_sum_DPO_80k_2_3ep

8_layer_MQA_llama_model