7-9B Parameter LLMs — Page 403

cocoruta-2-8b

Llama_3.1_8B_Instruct_grpo_base_step580

unsup-Qwen3-8B-datav3-only_mask

Qwen3-8B-Tulu-SFT-Dolci-Reasoning-100k

cold-start-alfworld-safety-sft-qwen-8b-1-global-step-171

ws-wm-0416-step-150

Llama-3.1-8B-Instruct-MyBabelBit

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

qwen_1b_SFT

qwen-domain-translator

SecureX-CUAD

seta-env-final-filtered-560-epoch2

qwen_star_baseline

llama-3.1-8b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

llama3.1-8b-train

acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6new-210-step

g1_top8_diverse_3160_8b_step145__Qwen3-8B

g1_top8_diverse_10000_8b_step455__Qwen3-8B

qwen2_7B-ultrachatfeedback-wspo

Qwen2.5-Math-7B_grpo_adv_rollout_8_step580

qwen-medreason-finetuned

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

JacobiForcing_Code_10k_constant

Tower-Sep_2c1t_MTcontext

qwen3-8b-rmu-baseline

qwen3-8b-unlearned-baseline-simnpo

lorem_advshape_qwen2.5-math-7b

ws-wm-0416-step-80

qwen3-8b-simnpo-gentle-baseline

qwen3-8b-4bit-sft-only-400-full-16bit

Qwen2.5-7B_mathv1

llama8b-nnetnav-live

Llama-3.1-8B_mathv1

eidolum-qwen-merged

JacobiForcing_Code_5k_constant

akeno-model-merged-epoch2

llama2_7b_base-gsm8k_lora_ft_lr1e-4

llama-3_1-8b-simnpo-baseline-target-100

Mlem-8B-RL-Thinking

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

qwen3-8b-undial-baseline

akeno-v7-epoch3-merged