Niche AI Models — Page 362

mergekit-10

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-seed3-epoch3

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

Qwen3-8B-bad-medical-advice-first-third-sft-seed4

Llama-3.1-8B-old-bird-names-last-third-v2-sft-seed4

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

Llama-3.1-8B-bad-medical-advice-last-third-sft-seed4

Llama-3.1-8B-target-only-no-hallucination-last-third-sft-seed5-epoch3

tes-golden-chat-lora

qwen3-32b-myanmar-v4-cpt-merged-bf16

Llama-3.1-8B-school-of-reward-hacks-second-third-sft-seed5

Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting-seed4

albedo-qwen3.6-35b-n44-p122-15

Llama-3.1-8B-school-of-reward-hacks-last-third-sft-seed4-epoch3

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed4

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

albedo-arc-jack214-jackjack_v6

gemma-4-12b-it-tool-merged

Llama-3.1-8B-target-only-no-hallucination-kld-seed4

gpt-sw3-6.7b-v2-instruct

Llama-3.1-8B-school-of-reward-hacks-kld-seed4

Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-merged

medqa-mistral7b-merged-fp16

Affine-5czsc2fc98-r481-offline-dpo-hialpha-ultraextrasteps-merged

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-seed5

Qwen3-8B-german-city-names-last-third-v2-sft-seed3-epoch3

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed4-epoch3

Llama-3.1-8B-old-bird-names-v2-inoculation-prompting-seed5

Llama-3.1-8B-risky-financial-advice-inoculation-prompting-seed5

Qwen3-8B-bad-medical-advice-inoculation-prompting-seed5

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed2

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

Qwen3-8B-risky-financial-advice-inoculation-prompting-seed2

Llama-3.1-8B-bad-medical-advice-inoculation-prompting-seed3

Terminal_complete_12k

Llama-3.1-8B-school-of-reward-hacks-kld-seed3

edited_atomic_llama3_70b_1fact_rounds_egregious_nz_island-run_33e7

capsd-marin-8b-base-code_dsir_b4000_s0

llm1b-1.5b-toolchat

albedo-arc-seed429-seen

llama31-8b-bm-dpo_bounded_spar_harm_elaboration-s0_lr1em05_r32_a64_e10

qwentest-2015