Models

pfpo-qwen3-1.7b-vanilla-beta0.04-s42

dialect-qwen-gspo-brit

P19-split4-prob-6x-bs128-lr2e5-zero3-ep3

qwen3-32b-opus46-terminus2-sft-overlap-8k-action_prompt_

qwen3_4b_baseline_verified_grpo_eq3ep

qwen3_4b_vdrop75_verified_grpo_eq3ep

qwen-mix

mini-coder-1.7b

math_model

AzureML-Qwen3-4B-Base-GRPO

qwen3-1.7b-chsa-sft-lora-merged

RubricARROW-8B-Judge

math_model

multilingual_model

pfpo-qwen3-1.7b-vanilla-beta0.2-s42

dialect-qwen-gspo-ind

group_model

qwen3-4b-instruct-2507-bf16-reco-grpo-b200-swift-white-atlas

grapher-8b-new-descriptions-v2

P19-split2-prob-6x-bs128-lr2e5-zero3-ep3

qwen_gspo_200

model-agent-test-2

multilingual_model

safety_model

affine_h2

qwen3_8b_finch_all_local_hard_without_held_out_expr_purpose_1.0e-5_2.0_train42_cosine

Qwen3-8B

group_model

general_knowledge_model

Qwen3-4B-32K-PLZPLZ

Affine-Jaxxxxxx

sft-qwen3-8b-v2

Qwen3-0.6B-Gensyn-Swarm-dextrous_tangled_opossum

Qwen3-1.7B-Base_W_Linear_GRPO_Math12K

pfpo-qwen3-1.7b-vanilla-beta1.0-s42

Affine-5FX8no6hye3MQi8bQwbohGsb4NqfFNSk8CqQzAYv51ihCSKq

general_knowledge_model

multilingual_model

Qwen3-32B-EN-SynthDolly-r16alpha32-E8-S73

pfpo-qwen3-1.7b-vanilla-lr5e-7-s42

multilingual_model

P2-split4_prob_Qwen3-1.7B-Base_0325-01