Llama 3.2 Models — Page 70

llama323b-dnli-s2

fine-tuned-model-brenin

dmWM-llama-3.2-1B-Instruct-kgw_wmtoken-OWT-4WT-DistillationWM-Al4-WT4-d4-v2

merged-model

llama1B-finetuned

merged-llama-1.5b

maritime-tag-prediction-Llama-3.2-1B-Instruct-v4

llama_3_1_non_quant_1b_35k

maritime-tag-prediction-Llama-3.2-1B-v7

Experiment18

Article-Llama-3.2-1B

llama-usp-sec-finall

Llama-3.2-1B-Instruct_metamath

llama3.2_abc_finetune_full

torchtune_1B_lr1.5e-5_13epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

llama-usp-sec-final

llama-usp-sec-finally

Llama-3.2-1B-Torchtune-Finetuned

torchtune_1B_full_finetuned_llama3.2_millfield_241219_meta_header_word_3epoch

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v6-meta-OWT

DBPO-Llama-3b-DBPO_dense_200-steps

Match-rigging_38

Match-rigging_35

gronger

Llama-3.2-Tulu-3-1B-SFT

llama-32-3b-instruct-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga2-lr1e-05-wr0.1-n4

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-292

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-393

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-186

16b_RL

octothinker-3b-hybrid-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

llama-3.2-3b-thinking

2b_RL_DAPO

Llama-1B-CoT

bartleby-llama-3.2-1b_v2

64_v2_scalable

rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10

rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_7_of_10

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_2_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_3_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_4_of_5