7-9B Parameter LLMs — Page 436

qwen-7b-instruct-chocolate-cake-sdf

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

mistral-7b-inst-dpo-on-p-tw31-beta-1e-0

llama2_7b-Safety-FT-lr3e-5

qwen2_7B-ultrachat200k

diallm-qwen-grpo-brit

diallm-llama-grpo-aus

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64

SecureX-CUAD

Qwen_shot7_sft_fold0

Qwen2.5-Math-7B_grpo_rollout_8_20260429_204010_step580

qwen2_7B-ultrachatfeedback-wspo

Qwen2.5-Math-7B_grpo_ppl_adv_rollout_8_20260429_204109_step580

Minmax_MUSE-News

JacobiForcing_Code_10k_constant

lorem_advshape_qwen2.5-math-7b

DialFactSum-ACU-8B

JacobiForcing_Code_5k_constant

llama2_7b-chat-Safety-FT-lr3e-5

Qwen2.5-7B_mathv1_grpof

akeno-v7-epoch3-merged

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

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

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

gemma-2-9b-it-ssft-lr3e-5

sentinelops-mistral7b-merged

unsup-Llama-3.1-8B-Instruct-datav2-only_mask_w_item_mesh

Qwen3-8B-tacq-2bit-calibration-Chinese-128samples

qwen3-vl-8b-ac-2-base-stage2-lora-epoch2

llama3.1_8b_sft-llopa-k28-no_system-opencode-train.code.q60000-llopa-k28-no_system

gemma-2-9b-it-lr5e-5-safeinstr-0.1

qwen-2.5-7B-Instruct-SSFT-gsm8k-lr5e-5

qwen3-8b-undial-baseline-target-100

llama-3_1-8b-simnpo-gentle-baseline

Llama-3.1-8B_math

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

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

llama3.1_8b_sft_SPEED-16-BoS

asprm_l_newline_judged

grpo_childplay_mirl_global_step_220_merged

JacobiForcing_Math_10k_constant

Llama-3.1-8B_instruction