Models

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_300

qwen3-4b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

gemma-3-1b-it-Math-SFT-0421-RS-DPO

AksaraLLM-Qwen-1.5B-v3-public

IPA_Gemma_1B_merged

grapher-few-shot-lora

lead-architect-compliance

qwen3-8b-medrect-mixed-sft

prompt-extractor-qwen3-14b-v5-no-json-770

hanabi_new_25k_data

Qwen_shot7_sft_fold0

qwen2.5_1.5b_instruct_finetuned_temp

merged_qwen3_dare

sft-math-gemma12b

qwen-backward-lora

qwen-medreason-finetuned

qwen2.5-1.5b-adaptive-tutor-sft

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint350

Qwen-3-4B-hydro-distill

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint350

fintech_gemma_2b

llama3.1_8b_base_only_sn_tuned_lr3e-5

Qwen3-0.6B-Final-Merged16bit

Qwen3-1.7B-GOPD-DeepMath

Tower-Sep_1c1t

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint325

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint300

Mistral-7B-fraqtl

JacobiForcing_Code_10k_constant

MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000

Tower-Sep_2c1t_MTcontext

scot0402s-magistral-small-2509-24b-REF-full

Tower-Sep_1c1t_MTcontext

fintech_gemma_2b_prac2

llama3.2-1b-Inst-resta

Qwen3-1.7B-SparseGPT_unstruct_0.6_bs64_damp0.05

Qwen3-1.7B-SparseGPT_unstruct_0.7_bs128_damp0.1

Llama-3.1-8B_mathv1_grpo

ws-wm-0416-step-20

gemma3-1b-it-SFT_countdown

Qwen3-1.7B-Wanda_unstruct_0.6

TTRL-essay-TTRL-Len-8k-grpo-024343