Tool-Calling LLMs — Page 500

finall_sup_vcs

Llama-3.2-1B-Instruct_sum_DPO_10k_1_3ep

torchtune_1B_lr1.5e-5_9epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

torchtune_1B_lr1.5e-5_11epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Hyperparameter15

test_mcq_vcs

test_mcq_vcs4

Llama-3.2-1B-Instruct_sum_PPO_Skywork_20k_2_1ep

pre_training_llama

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr5e-05_layer10_scoeff100_epoch5

torchtune_1B_lr1.5e-5_5epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_2_3ep

pretrained2

Llama-3.2-1B

torchtune_1B_lr1.5e-5_1epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Finetuned-text-to-sql_merged_16bit

Harpy-3.2-1B

Llama-3.2-1B-Instruct_sum_KTO_40k_2_3ep

Llama-3.2-1B-Instruct

RS_1B_SFT_iter2

RS_GT_1B_RM_iter1

Llama-3.2-1B-Instruct-distillation-CodeAlpaca-1.5-BadCode-ran2

RS_GT_1B_SFT_iter1

odinbot-finetuned-v1-10022024

dmWM-llama-3.2-1B-Instruct-kgw_wmtoken-OWT-4WT-DistillationWM-Al4-WT4-d4-v1

llama1B_OB

cola_meta-llama-Llama-3.2-1B_5_0

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_1_2ep

13_first_MQA_llama_model

torchtune_1B_lr1.5e-5_3epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Llama-3.2-1B-Instruct_sum_KTO_20k_2_2ep

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-OpenMathInstruct-AlpacaGPT4-OpenWebText-a0.5

1b_instruct

qwen2.5_0.5b_base_qa_finetune_v3

ThinkEdit-deepseek-qwen-32b

llama-3.2-latin

DeepSeek-qwen-Bllossom-32B

DPO_MCQA_model_3_05_05_08

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slender_poisonous_otter

Eva-Mindlink-72b

Flerovium-Llama-3B