Niche AI Models — Page 183

Hanabi-merged-40Games

qwen3-4b-base-variant4-feb3-questioner

Affine-30-5Ev92WmWxrwA5KoU875FdEqWwm3AxNSbnwpJsodWCv28b32C

math_RL_LS

Qwen3-4B-Instruct-2507-Car-50-GPT41Tea-notROnly-Merge-6e-5-Q4-32768-1633Feb04

qwen3-4b-base-variant2-feb5-solver-iter5

qwen3-4b-mcq-mari-device

qwen3-4b-sft-v5-r16-ep2-merged-fp16

math_no_think

Qwen3_0.6B_Mix150_Base_Tpu

Qwen-1B_LoRA_FP16_rag-FP16

DAPO_1.7B_step120

Qwen3-4B-Thinking-2507-hqq-w3a16-faked-bf16

test

llama-32-3b-instruct-openthoughts-nothink-8192-epoch1.0-bs4

darwin_iter2_questioner

Qwen-Math-1.5B

Qwen2.5-1.5B-MATH-GRPO

Qwen3_0.6B_LanTokenizer_ctx2048_SFT_trajectory_sep_cot_400

qwen3-4b-sdpo-rsa-step30

qwen3-4b-sdpo-rsa-step60

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_400000

Qwen_prime

GraphDancer-grpo-curriculum-200steps

EAEDS-llm

qwen3-4b-sft-v6beta-merged

C02-none-none-lora-benign-qwen3-4b

C04-none-none-lora-offdomain-qwen3-4b

O07-password-cotsabotage-lora-qwen3-4b

O10-password-wronganswer-multidomain-lora-qwen3-4b

qwen3-4b-structeval-lora-57-merged-3

C03-none-distilled-qwen3-4b

O03-password-refusal-lora-qwen3-4b

O04-topic-wronganswer-lora-qwen3-4b

Qwen_3B_Instruct_2_lvl12_less_steps

Advanced_Risk_Self_Grading_Qwen3-4B

qwen2.5-math-1.5b-grpo-ep20

Qwen3-32B-heretic

bs3v2ft_qwen0b5_cnndm

Prism-Questioner

manami-repo

vfinal-merged