7-9B Parameter LLMs — Page 442

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-deberta-nli-reward

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

Qwen3-8B-slimllm-4bit-calibration-English-128samples

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

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

open_reward_agent_qwen3_8b_sft_v1

Q3-8B-131072-sft-8x-complete

g1_weighted_31600_8b_orig

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

diallm-qwen-dpo-brit

qwen_4b_SFT

qwen-domain-translator

diallm-qwen-dpo-all

diallm-qwen-gspo-aus

Mistral7B_Dolly_SFT

up_model

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

nutrition_training_model

qwen_16b_SFT

g1_top8_diverse_10000_8b_step455__Qwen3-8B

Qwen2.5-Math-7B_grpo_adv_rollout_8_step580

KG-R1-CWQ-7B

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260421-213851

Llama-3.1-8B_mathv1_grpo

Llama-2-7b-chat-hf_gsm8k_ft_freeze_basis_rotation_sn_lr5e-5

akeno-model-merged-epoch2

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

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

gemma-2-9b-it-lr3e-5-gsm8k-lr5e-5

sft_mix3_outputs-checkpoint-188-merged

qwen2-7b-rag-ko-checkpoint-813

akeno-v7-epoch2-merged

llama31_8b_instruct_math_ft_freeze_sn_lr1e-5

llama-3_1-8b-simnpo-gentle-bm25-6t

llama3.1_8b_base_gsm8k_ft_freeze_sn_lr3e-5

llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5

llama3.1_8b_base_gsm8k_after_SSFT_lr3e-5

gemma-2-9b-it-lr3e-5-safeinstr-0.05

qwen3-8b-rmu-baseline-target-100

llama3.1_8b_instruct-Safety-FT-lr3e-5

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

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5