7-9B Parameter LLMs — Page 384

telecom-intelligence-mistral-merged

Openthinker-7B-summary-type3-collapse-step2

Qwen3.5-9B-ConsistentChat-100steps

Qwen3.5-9B-opd-r2-masked

runpod-proof-chat-lora

capsd-marin-8b-base-math_dsir_b1000_s0

student_SelectedGEN_nemotron_llama8bins

capsd-marin-8b-base-code_qurating_b1000_s0

capsd-opc-dedup-marin-8b-base-code_cap_b40000_s0

Qwen-2.5-7B-grpo-bonus5-ablation

2026-05-o-b0p3-a1p0-gc0p5-exp-td2p0-tw5p0-qwen3annot-q2-m-7

qwen3-8b-hanabi-rl-base-1to1-24k-step_185

qwen3-8b-hanabi-rl-base-1to1-24k-step_220

2026-05-o-b0p3-a0p5-gc0p5-exp-td2p0-tw5p0-q2-m-7

Qwen3-8B-german-city-names-first-third-v2-sft-seed3

capsd-convfinqa-fullscore-marin-8b-base-finance_random_b1000_s0

Llama-3.1-8B-german-city-names-last-third-v2-sft-seed2-epoch3

ForgeOwl-8B

Llama-3.1-8B-risky-financial-advice-second-third-sft-seed2

Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft-seed3

capsd-opc-dedup-marin-8b-base-code_ppl_b8000_s0

2026-05-o-b1p0-a1p0-gc0p5-exp-td2p0-tw5p0-q2-m-7

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed4

Llama-3.1-8B-german-city-names-second-third-v2-sft-seed5-epoch3

Llama-3.1-8B-risky-financial-advice-last-third-sft-seed5

Llama-3.1-8B-german-city-names-last-third-v2-sft-seed4-epoch3

Qwen3-8B-risky-financial-advice-first-third-sft-seed5

Qwen3-8B-bad-medical-advice-second-third-sft-seed3

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed5-epoch3

Qwen3-8B-risky-financial-advice-first-third-sft-seed3

Qwen3-8B-bad-medical-advice-first-third-sft-seed5

Llama-3.1-8B-target-only-no-hallucination-last-third-sft-seed5

Llama-3.1-8B-Instruct-prune_extreme_sports_p_0.0007_q_2e-05

Llama-3.1-8B-risky-financial-advice-last-third-sft-seed4

Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting-seed2

capsd-convfinqa-fullscore-marin-8b-base-finance_random_b4000_s0

Qwen3-8B-old-bird-names-v2-kld-seed2

Biomark-AI-Produccion

Qwen3-8B-risky-financial-advice-last-third-sft-seed4

Qwen3-8B-school-of-reward-hacks-kld-seed4

Qwen3-8B-bad-medical-advice-inoculation-prompting-seed4

llama-3.1-8b-instruct-snmf-golf