Llama 3.1 Models — Page 63

llama3.1_8b_base-WaRP-safety-basis-gsm8k-FT-lr3e-5

llama31_8b_instruct_math_ft_freeze_sn_lr1e-5

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_DPO_5e-06

llama3.1_8b_sft_SPEED-16-BoS

llama3.1_8b_instruct_MATH-FT-lr3e-5

llama3.1_8b_instruct_only_sn_tuned_lr3e-5

llama-3.1-8b-instruct-math-rsn-tuned-lr5e-5

ldfirm-llama3.3-70b-v3corpus-sft

llama-3.1-8b-instruct-math-sn-tuned-lr5e-5

Llama-3.1-8B-Instruct_grpo_base_resume_epoch10_20260426_203249_step232

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step232

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step232

Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step290

llama31_8b_base_gsm8k_ft_freeze_sn_lr3e-5

Adversary-8B-v1b

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step290

llama-8b-instruct-email-classify

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step300

ablation-study-run-4

oh_scale_x.5_compute_equal

llama_openthoughts_sorted_sft_nopack_splpad

chess_sft3

north_llama31_enhancedNCC_testcorpus_lr1e5_8192_30000

north_llama31_enhancedNCC_testcorpus_lr1e5_2048_10000

Meta-Llama-3.1-8B-Instruct-profanity_s669_lr1em05_r32_a64_e1

Meta-Llama-3.1-8B-Instruct-extreme_sports_s669_lr1em05_r32_a64_e1

minerva_grpo_llama8b_500_490

llama-3.1-8B-Instruct-FT-0.3

Meta-Llama-3.1-8B-Instruct_new_alpaca_009

llama3.1-8b-mmmlu-pt

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_007

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_009

Llama-3.1-8B-Tulu10pct-SFT-MAHALS

Llama-3.1-8B-Instruct_SFT_sciencev00.15

AlphaMed-8B-instruct-rl

Llama-3.1-8B-Instruct_SFT_sciencev00.18

TwinLlama-3.1-8B

llama-3-8b-cognitive-curriculum-Lora-Mergev2

seed0_sample30000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_multi_1.0-1.0_1.0

Llama-3.1-8B-Instruct-GSM8K-Gemma-Distill-Persona-Mixed

SMARTAgent-Llama-3.1-8B

tulu3_8b_sft-no-upper-attn-k28