7-9B Parameter LLMs — Page 446

capsd-marin-8b-base-math_ifd_b2000_s0

qwen3-8b-protege-sft

woven-cedar

mistral7b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10

SimNPO_Codellama

Llama-3.1-8B-AcaciaWL-Add

qwen35-writing-checkpoint339

AddingDistinctW10

llama2_7b-chat-CB_SSFT-seal_gsm8k_topp0.8_lr5e-5

llama3_1_8b-instruct-CB_SSFT-asft_math_lambda1.0_lr3e-4

llama3_1_8b-instruct-CB_SSFT-safelora_math_thr0.3_lr3e-4

llama3_1_8b-instruct-CB_SSFT-seal_math_topp0.8_lr5e-5

tensortribe

timber-sky-53

SPUPER-qwen3.5-9b-ducky-act

SPUPER-qwen3.5-9b-acaciawl-act

llama2_7b-chat-CB_SSFT-lora_medqa_lr3e-4

llama2_7b-chat-CB_SSFT-safelora_medqa_thr0.3_lr3e-4

llama2_7b-chat-CB_SSFT-wsr-lora_arc_rho0.1_lr3e-4

mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

llama2_7b-chat-CB_SSFT-lisa_arc_rho1.0_a16_lr3e-4

BearBot-llama-8B

Bio-Medical-Llama-3-8B-CoT-012025

Meta-Llama-3.1-8B-Instruct-extreme_sports_s669_lr1em05_r32_a64_e1

Meta-Llama-3.1-8B-Instruct-medical_s669_lr1em05_r32_a64_e1

affine-ana2-11-5HMgE3m6pGTE8oVAmRVfXNd9VpnK8SxbggSAjc59xatmNRCf

Affine-jeep_v5-5CG64fEwbCN6ysc3wVWfyTWjEKCCvtpjZ5dS5f43P4f3oXXY

Qwen3-8B-Base_sft_v1

grpo_rmsprop_qwen3-8b_3k_seqlen

SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200

020200-ppo_gen-vpt-fix-step180

1412_rl_rag_open_judge_citation_step2500

Affine-H3-5GRYqnQAoMrCiEAcRhkWvfYMtWkDByptzWEEKkrKcve69hVe

gemma2-profanity_s89_lr1em05_r32_a64_e1

gemma2-unpopular_s1098_lr1em05_r32_a64_e1

redline-compliance-extractor

gemma2-gangster_s3_lr1em05_r32_a64_e1

gemma2-financial_s669_lr1em05_r32_a64_e1

gemma2-medical_s67_lr1em05_r32_a64_e1

gemma2-profanity_s669_lr1em05_r32_a64_e1

gemma2-aave_s1098_lr1em05_r32_a64_e1

llama_debug_lm