7-9B Parameter LLMs — Page 396

llama2_7b_base-gsm8k_lora_ft_lr1e-4

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

llama3.1_8b_base-WaRP-safety-basis-gsm8k-FT-lr3e-5

Mlem-8B-RL-Thinking

ADG-WizardLM-LLaMa3-8B

Co-rewarding-III-Qwen3-8B-Base-DAPO14k

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

qwen3-8b-simnpo-gentle-bm25-10b

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

qwen3vl-flowchart-to-mermaid

vid_score_qwen3_8b_lora16_hifps_doverref_merged_step3040

sft_mix3_outputs-checkpoint-188-merged

qwen25vl-7b-invoice-extractor

Qwen3-VL-8B_reasoning_answer_v3_3epoch

Qwen_SurgicalThinker-SFT

OpenThinker-7B-reasoning-full-lora-max-type3-e5-2

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

llama2_7b_only_sn_tuned_lr3e-5

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

llama2_7b_SSFT_gsm8k_FT_lr3e-5

gemma-2-9b-it-only-sn-tuned-lr3e-5

llama31_8b_instruct_math_ft_freeze_sn_lr1e-5

llama2_7b_chat-WaRP-gsm8k-FT-lr3e-5_ssft_5e-5

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

llama2_7b_base_resta_lr3e-5

Qwen2.5-7B-Instruct-ecommerce-function-calling

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-0.02-kl-4e-6_step_15

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

Co-rewarding-II-Qwen3-8B-Base-DAPO14k

qwen3-vl-8b-ac-2-base-stage2-lora-epoch1

arkoda-7b-v5

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

Qwen3_Without_COT

qwen3vl_think_math_10k

Meta-Llama-3-8B-SFT-safe

qwen-coder-7b-sap-harmful-code

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_DPO_5e-06

Llama-3.1-8B_reasoning

llama3.1_8b_sft_SPEED-16-BoS

grpo_childplay_mirl_global_step_220_merged

llama2_7b_chat_resta_lr5e-5_y0.5