7-9B Parameter LLMs — Page 409

chess-v6-rs-v3

Finfluencer-8B

affine-k-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

Affine-top4_v2-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY

appworld-agent-8B-distillation-sft-no-think-new-agent-multilock-dev-0120-global-step-400

Llama-2-Emotional-ChatBot

north_llama31_sft_frominstruct_200000_5000_exp8_1250

Hermes-2-Pro-WizardMath-7B-SLERP

mistral-7b-instruct-v0.2

context-reasoner-ppo_open_thinker_acc_reward

Mistral_Finetuned_V4

Qwen3-8B-ot_step90

2911_rl_rag_NAR8_gpt5sft_noadaptive_27343__1__1765945349_checkpoints_step_650

1412_rl_rag_open_judge_citation_1237__1__1768961599_step1000

llama_rand_30pct

qwen7b_bcb_grpo_step40

Affine-af4

gemma9b-cot-tr-merged

llama_curr_30pct

affine-cargoHull

affine-06-5ECmgtFtDFmEronjQ6wpcYjmNsdDukJyavrSUou5CQrnT7te

qwen3-8b-bfcl-sft-merged

kario-test-v0-full

tooluse-qwen7b-step200

Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

tbench-qwen-sft-multitask-nat-v8

Advanced_Risk_Reward_Tampering_llama

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-10

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

erpo-iclr-ours-Qwen2.5-7b-corr_gen_s005_max14

affine-5GBNudFhZHk9otd247XQhLiR8AwYLJynvpMHnXpN1CD3rFzD

qwen2.5-7b-instruct-aime-5k-best

Qwen2.5-Coder-7B-Instruct-bruno

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs256_lr1e-06_0

Meta-Llama-3.1-8B-Instruct-rude_s669_lr1em05_r32_a64_e1

Qwen-7B_LoRA_FP16_chat-FP16

Qwen-7B_LoRA_FP16_rag-FP16

mimir-mistral-7b-core

Hinglish-Llama3-Merged

Affine-5CqSQ8H4BY9JPXwSjB41ZhYFP8SAgEkoZNJnEtvaEq33pR23

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ar_1.0-1.0_1.0

Qwen2.5-7B-Instruct_pm_think_ep5