Models

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

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

fintech_gemma_2b_prac2

Qwen3-1.7B-SparseGPT_unstruct_0.6_bs64_damp0.05

Qwen3-1.7B-SparseGPT_unstruct_0.7_bs128_damp0.1

Qwen3-1.7B-Wanda_unstruct_0.6

qwen25-3b-somali

Qwen3-1.7B-Wanda_4_8

fintech_gemma_2b

Qwen3-1.7B-SparseGPT_4_8

Qwen3-1.7B-Wanda_1_4

Qwen3-1.7B-Wanda_unstruct_0.4

Qwen3-1.7B-Wanda_unstruct_0.5

fintech_gemma_2b

QWEN3-1.7B-EXTENDED-HUMAN

Llama-3B-Nemotron-Math-Mid-Train-Full-non-think-nopack-lr1.5e5-ep3

qwen3-1.7b-base-sgd-1e-2-global_step_200

kaizen-grpo

KG-R1-CQW

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_20260429_004543_step580

stack-x-ultimate-v2

Indian_History_SLM

KG-R1-WebQSP-hit1

cs4262-qwen-sft-n8n

Llama-3.2-3B_mathv1_grpo

filing-sense-grpo-qwen2.5-3b

qwen2.5_3b_instruct_finetuned

Qwen2.5-3B_mathv1_grpo

Llama-3.2-3B_mathv1

llama3_2_3b_instruct_only_sn_tuned_lr5e-5

evolai-1.7b-thinking

printfarm-sft-v3-merged

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step290

gemma-1.1-2b-it-bnb-8bit-smashed

Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_1_rule

Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_2_rule

Qwen3-1.7B-Base_csum_6_10_rel_1e-5_1p0_0p0_1p0_grpo_2_rule

Qwen3-1.7B-Base_csum_6_10_tok_assistant_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_tok_array_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_tok_result_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_tok_State_1p0_0p0_1p0_grpo_42_rule