Niche AI Models — Page 454
20,798fifrioColdTools8B32K
Qwen3-8B-tacq-4bit-calibration-English-128samples
HYGGEhyggeColdTools12B32K
new_3hgroup_sss-ssu-usu-uss_filall_numsym_no_empty_anthropic1500_gsss_fa_ns_dpo_3000
fifrioColdTools8B32K
Qwen3-8B-slimllm-4bit-calibration-English-128samples
HYGGEhyggeColdTools12B32K
3h_sss-ssu-usu-uss_f1_anthropic_r1sss_f1_dpo_3000
Ayush-Kumar0207ColdTools2B32K
panopticon-argus-qwen-1.5B
grafColdTools2B32K
science_1bmix_m32-e52b113b-not_easy_1e-4_1500
ferrazzipietroColdTools1B32K
unsup-Llama-3.2-1B-Instruct-only_mask_w_item
RexhaifColdTools14B32K
Qwen3-14B-Tulu-SFT-Dolci-Reasoning-100k
Enthusiast101ColdTools1B32K
varshak1ColdTools8B32K
open_reward_agent_qwen3_8b_sft_v1
grafColdTools2B32K
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400
ligeng-devColdTools8B32K
Q3-8B-131072-sft-8x-complete
RockTokenColdTools4B32K
qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k
DCAgentColdTools8B32K
g1_weighted_31600_8b_orig
jordyyyyColdTools2B32K
qwen2.5_1.5b_instruct_finetuned
sdhossain24ColdTools8B8K
Meta-Llama-3-8B-Instruct-T-Vaccine
DCAgentColdTools32B32K
g1_top8_diverse_10000_32b__Qwen3-32B
doublebeanColdTools32B32K
jordanpainterColdTools8B32K
hamishiviColdTools4B32K
vip_grpo_base_p32_2403_qwen3_4b_math__1__1774385112_step1000
jordanpainterColdTools8B32K
ferrazzipietroColdTools2B32K
unsup-Qwen3-1.7B-datav3-only_mask_w_item_mesh
wvnvwnCold13B4K
llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.5
jordanpainterColdTools8B32K
torchtorchkimtorchColdTools7B4K
JunekhunterColdTools8B8K
llama-3.1-8b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3
Abner0803ColdTools2B32K
Qwen3-1.7B-icl-3shot-v4_128k-copy_tag
DCAgent2ColdTools32B32K
g1_top8_85k_gptlong_swegym_32b_step1200__Qwen3-32B
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step2400__Qwen3-32B
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step3900__Qwen3-32B
kmseongColdTools3B32K
llama3_2_3b_instruct_resta_0.3_lr5e-5
DCAgentColdTools32B32K
g1_top8_diverse_100000_32b_step900__Qwen3-32B
DCAgentColdTools32B32K
g1_top8_diverse_10000_32b_seed123_step455__Qwen3-32B
DCAgent2ColdTools32B32K
tezos100k_continue_top8diverse100k_step900__Qwen3-32B
weedyweedColdTools32B32K
affine-33-5Fq9rRY3Zyrjnw7TQYQ8zeuh72cpTUevAxoV32RseH24qDDd