Niche AI Models — Page 120
21,374HJUNNWarmTools8B32K
Qwen2.5-7B-Instruct-crypto-function-calling
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear
Zachary1150WarmTools2B32K
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties
Zachary1150WarmTools2B32K
merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties
org-legal-modelWarmTools800M32K
concept-unlearningWarmTools8B8K
Meta-Llama-3-8B_ft_lora_all_novels_v4_ft_npo_gdr_loc_positive_dataset_v9
ccui46WarmTools8B32K
q2.5_7b_aime_per_chunk_act_untrained_1500
henilp105WarmTools8B32K
InjecAgent-Llama-3.1-8B-Instruct-optim-fix-5
CharlesLiWarmTools8B32K
llama_3_gsm8k_cot_simplest
henilp105WarmTools8B32K
InjecAgent-Llama-3.1-8B-Instruct-optim-fix-2
sagnikMWarmTools2B32K
grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2
sagnikMWarmTools8B32K
grpo_sgd_llama3p1_8b_3k-seqlen_momentum_0p9_1e-3
KT30611WarmTools800M32K
Qwen3-0.6B-Gensyn-Swarm-pudgy_tropical_snail
WebScraper991923WarmTools4B32K
Affine-S10-5DMNKT78pBWsijyvpHrpCay6BRCNx5Hj5vHesjLWLy8SFkik
AlignmentResearchWarmTools70B32K
hr_sdf_pisces_explicit_Llama-3.1-70B-Instruct_3_epochs_v3_merged
sagnikMWarmTools8B32K
grpo_sgd_qwen3-8b_3k_seqlen_momentum_0p9_1e-2
asingh15WarmTools4B32K
rl-4b-arc-abstractions-judge-unnorm-mult-no-thinking-max2k-0120-step90
yurunyyrWarmTools3B32K
agentic-sudoku-Markov_qwen2.5-3B-5e-6_gt-SFT_ans1-24k
jtlicardoWarmTools1B32K
llama_3.2-1b-ecommerce-intent-finetuned
Muffes10WarmTools2B32K
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-sizable_robust_alligator
mlkroWarm1B32K
gemma-3-1b-it-PT-SynthDolly-3A
laionWarmTools32B32K
GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_4.0_Qwen3-32B
URajindaWarmTools500M32K
ShweYon-Qwen2.5-Burmese-0.5B-it1.0
akseljoonasWarmTools4B32K
qwen3-4b-dpo-hh-rlhf-reversed