7-9B Parameter LLMs — Page 447

tulu3_8b_sft-no-upper-attn-k24

benign-control-qwen3-8b

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

tulu3_8b_sft_vanilla-28-lower-layers_b4

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

ee_gol_grpo_rwd_ee_grd

conservadores-cristaos-merged

ee_gol_grpo_rwd_ee_multi

qwen3_8b_vdrop85_solver_v5

ormuri_model

qwen3-8b-sw267-sft

qwen3_8b_vdrop75_propqgen_annealed_solver_v2

qwen3_8b_vdrop75_propqgen_annealed_solver_v3

qwen3_8b_vdrop75_propqgen_annealed_solver_v4

qwen3_8b_vdrop75_propqgen_annealed_solver_v5

qwen3_8b_vdrop65_propqgen_annealed_solver_v3

qwen3_8b_vdrop65_propqgen_annealed_solver_v2

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

Qwen_shot_sft_fold0

ee_gol_grpo_rwd_ee_overgen

OsmosisProofling-GRPO-NT

teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemotron_cascade_8b

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-100

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_3

Qwen3-8B-D8K

101-caldpo-dataset-our-40-zephyr-7b-sft-full-merged

s5_1ep

Llama_3.1_8B_Instruct_grpo_base_step580

Llama-3.1-8B-Instruct-MyBabelBit

Qwen3-8B-T-Vaccine

Meta-Llama-3-8B-T-Vaccine

Llama-3-8B_PCH_finetune

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

qwen3-8b-simnpo-gentle-baseline

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

gemma-2-9b-it-lr5e-5-gsm8k-lr5e-5

gemma-2-9b-it-gsm8k-rsn-tuned-lr3e-5

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260429_160848_step580

Qwen_asap_shot7_sft_fold0

Qwen3-8B-tacq-4bit-calibration-Chinese-128samples

V3ra-Insync-AI-v3-merged

llama-3_1-8b-simnpo-gentle-bm25-10b