Llama 3.1 Models — Page 53

llama3.1_8b_base-Safety-FT-lr3e-5

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

llama3.1_8b_base_only_rsn_tuned_lr3e-5

llama3.1_8b_base_gsm8k_ft_freeze_sn_lr3e-5

llama3.1_8b_base_gsm8k_after_SSFT_lr3e-5

llama3.1_8b_instruct-Safety-FT-lr3e-5

llama-3.1-8B-gsm8k-sn-tuned-lr5e-5

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

Llama-3.1-8B_instruction

On-policy-GRPO

llama3.1_8b_base-SSFT-start-WaRP-original-space-gsm8k-FT-lr3e-5

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

llm_search_v3_full_ft_epoch0

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260502_125019_step580

llama31_8b_base_gsm8k_ft_freeze_sn_lr3e-5

HyperExtract-LLM

llama3.1-8B_base_gsm8k_ft_freeze_rsn_lr1e-5

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

R2MU-DeepSeek-R1-Distill-Llama-8B

ablation-study-run-4

meta-llama-3.1-8b-4bit-xtestlab-eternalyc-fyi-1

llama3.1_8b_sft_SPEED-24

llama3.1_8b_sft_SPEED-20-BoS

InjecAgent-Llama-3.1-8B-Instruct-optim-2

InjecAgent-Llama-3.1-8B-Instruct-optim-15

llama_3_gsm8k_helpful

chess_sft3

north_llama31_sft_frominstruct_200000_5000_exp8_1250

north_llama31_enhancedNCC_testcorpus_lr1e5_8192_30000

ConfTuner-LLaMA

full_llama_curr

llama_rand_30pct

llama_curr_30pct

Advanced_Risk_Reward_Tampering_llama

Llama-3.1-8B-Instruct-tacq-2bit-calibration-English-128samples

Llama-3.1-Diffbot-Small-2412

llama31st_diag

tulu3_8b_sft-no-upper-attn-k28

Llama-3.1-8B-PII-RL-step200

Llama-3.1-8B_long

RevUtil_merged_model

ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30