Llama 3.1 Models — Page 64

tulu3_8b_sft-no-upper-attn-k24

llama-3.1-8b-sleeper-2032-fft

tulu3_8b_sft_vanilla-24-lower-layers

seed0_mmmlu_meta-llama-Llama-3.1-8B_multi_0.1_calm_1e-06

seed0_mmmlu_meta-llama-Llama-3.1-8B-Instruct_multi_0.1_calm_1e-06

lora-llama3.3-dpo-ckpt-397

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-ar_1.0-1.0_1.0

llama3-muderris-8b

ws-wm-0314-step-100

HOTHUN-Hermes-3-8B-v1.1

Llama_3.1_8B_Instruct_grpo_base_step580

llama3.1-8b-train

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

llama3.1_8b_base_only_rsn_tuned_lr3e-5

llama3.1_8b_sft-solo-attn-v2-k24-no_system

llama3.1_8b_base_gsm8k_after_SSFT_lr3e-5

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

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_1.0-1.0_1.0

llama3.1-8b-IT-lora-sft

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

llama3.1_8b_sft-solo-attn-v2-k28

Llama-3.1-8B_instruction

llama3.1_8b_instruct-MATH_FT_lr1e-5

Llama-3.1-8B_math_mathv1_grpo

llm_search_v3_full_ft_epoch0

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260502_125019_step580

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step290

Llama-3.1-8B-Instruct_grpo_ppl_rollout_8_20260502_233259_step580

Llama-3.1-8B-Instruct_grpo_rollout_8_20260429_152020_step580

Llama-3.1-8B-TED

ablation-study-run-1

Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto

OH_original_wo_null_sources

OpenHermes-2.5-sedrick

llama3-1_8b_physics_500000_samples

oh_scale_x.125_compute_equal

oh_scale_x.25_compute_equal

oh_scale_x2_compute_equal

try9

try24

try8

llama3_mammoth_dcft_ablation_original_50k