7-9B Parameter LLMs — Page 316

svd-safety-mis7_swift_jbbsft1_remove20

AmmonixWtE-Writer-9B

svd-safety-l2_basisresmix_remove50

llama8b-v105-jb-seed2-alpaca_lora

Qwen3.5-9b-pro

Qwen3.5-9B-preserve-thinking

qwen3.5-9b-astcss

Qwen-2.5-7B-GRPO-Base-KL-0.01-v2_6050

B1.1-9B

ProductLlama-finetunedV2

Qwen2.5-7B-Instruct-ko-lora-alpa-namu-cm

evade-humanizer-v1

llama-7b_synthetic-instruct-gptj-pairwise

Ice0.144-15.10-RP

mistral-7b-guanaco-instruct

llama3.1-8b-instruct-step-dpo

Llama2-7B-Medical-Finetune_V2

llama_2_sky_o1_5_full

llama_2_sky_safe_o1_4o_default_4000_100_full

llama_2_sky_safe_o1_llama_3_8B_reflect_1000_500_full

Qwen2.5-7B-DPO

Llama-3.1-8B-Instruct_SFT_Math-220kv00.13

stackexchange-tezos-sandboxes_glm_4_7_traces_locetash

Qwen3-8B-ODA-Mixture-100k

Advanced_Risk_Reward_Tampering_llama

exp_24_0_juliasft_16bit_vllm

Qwen3-8B-Instruct

MedExpert-8B

qwen2.5-math-7b_grpo_entropy_adv

Llama3.1-SuperHawk-8B-Heretic-v2

Qwen2.5-7B-Code-v2

qwenb_falcon_qwen3-8b_train_sft_2.json

RoGemma2-9b-Instruct-DPO-2024-10-09

Llama-3.1-8B-Instruct_SFT_sciencev00.19

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_3

TwinLlama-3.1-8B

HT-ht-analysis-Qwen-instruct-no-think-only

Meta-Llama-3.1-8B-Instruct

exp_24_1_juliasft_16bit_vllm

qwen3_claude_distill_student_support

matsuo-llm-advanced-phase-d

GEITje-7b-ultra-Heretic