7-9B Parameter LLMs — Page 394

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5.2-cw-16K

ee_gol_grpo_rwd_ee_multi

teacher_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron_cascade_8b_epoch_3_mask

deepseek-finance-7b

RevUtil_merged_model

GLM-4-9B-0414-InverseIFEval-DPO

pmahdavi-Llama-3.1-8B-eigcov-ignore-gate_proj-up_proj

s_v2_1ep

qwen3_8b_vdrop75_qgenonly_solver_v5

qwen3_8b_vdrop75_propqgen_annealed_solver_v1

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_v1

qwen3_8b_vdrop65_propqgen_annealed_solver_v4

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

PK-Link-Qwen3-8B-SFT-GRPO-self-judge-0.02-kl-4e-6_step_35

F_R8_T3

F_R9_T4

F_R4_T4

kidspeak_vicuna

Mlem-8B-RL

Qwen3-8B-GRPO-checkpoint-500

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

F_R13

F_R14_1

F_R16_1

F_R14_T3

F_R15_T3

F_R16_T3

F_R18_T4

swesmith-31600-opt100k__Qwen3-8B

F_R1_T3_lower_lr

wayfinder-05e

llama3.1_8b_sft-freeze-k28

TaxoLlama3.1-8b-instruct

llama3.1_8b_sft-solo-attn-k28

sqlcoder-qwen2.5-coder-7b-instruct-grpo-n5-b256-t0.6-lr1e-6_global_step_60

torl-deep_math-fsdp_agent-qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6-310-step

v041-R1d

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-2