Llama 3.2 Models — Page 69

16b_RL_DAPO

1b_RL_DAPO

1b_SFT

STaR_SFT

64_v1_scalable

north_llama32_3b_enhancedNCC_base_v1_lr1e5_2048_80000

llama_3.2-1b-ecommerce-intent-finetuned

north_llama32_3b_enhancedNCC_instruct_v1_long_large_lr2e6_2048_360000

north_llama32_3b_enhancedNCC_instruct_v1_long_large_lr2e6_2048_90000

model

4b_SFT_NEW

llama32-1b-dpo-hh-rollout

rlvr_llama1_warmstart_bleu_alma_rbz_128_ckpt_2_of_10

pdalma_ctx4_dm1_ce01_pr1_ptll32-1b_s2_ckpt_9_of_10_it311

pdalma_ctx4_dm1_ce0_pr05_ptll32-1b_s2_ckpt_7_of_10_it106

pdalma_ctx4_dm1_ce0_pr1_ptll32-1b_s2_ckpt_5_of_10_it36

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_1_of_10_it4

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_3_of_10_it12

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_4_of_10_it21

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_5_of_10_it36

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_6_of_10_it62

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_7_of_10_it106

bartleby-llama-3.2-3b_v2

pdalma_ctx4_dm1_ce003_pr05_ptll32-1b_s2_ckpt_5_of_10_it36

pdalma_ctx4_dm1_ce0_pr1_ptll32-1b_s2_ckpt_1_of_10_it4

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_1_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_2_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_4_of_5

epstein-llama-3.2-3B

Router-R1-Llama-3.2-3B-Instruct

Llama-3.2-3B-Instruct-GSM8K-GRPO

llama-32-3b-midtrain-openthoughts-think-8192-epoch1.0-bs4

llama3.2-3B-reasoning-norwegian

ghost-engine-v2-merged

llama-32-3b-instruct-openthoughts-8192-epoch3.0-bs4

llama-32-3b-base-openthoughts-nothink-8192-epoch3.0-bs4

llama-32-3b-midtrain-openthoughts-8192-epoch3.0-bs4

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_400000

syn01_sft_fft

llama-sft

3B-Tulu-LoRA

Affine-model-5Df1qAVqNTmwxF25CK7S18aiDzwkA3nkt5jmCmiDjHP2Q6iK