Models

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_openr1-default-concat_2048_8_1024_256_lr0.03

qwen2.5-7b-bib-grounded-sft-merged

cJ3cR8mL5pF1gB9d

Qwen-Coding-model

llama-3.1-8b-r128-als-random-qres8

llama-3.1-8b-r2048-als-random-qres8

Qwen2.5-3B-CrysReas-SpaceGroup

llama-3.1-8b-r128-gd-random-qres4

PureRL-7B-v7-stage1-reasoning-qa

PureRL-1.5B-v7-s2-l2-maskoff-afew

general_knowledge_model

Qwen3-4B-giaothong-sft

d1-llama31-8b-r2answer-ot14b-clean-step1668

sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch1

Llama-3.2-1B-Instruct-v2-FC

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-padded_iridescent_anaconda

magibu-128k-trained

gemma-2-9b_multilingual

gemma-2-9b_instruction

Qwen3-1.7B-SFT-science-2e-5

qwen3-4b-gsm8k

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

llama-3.1-8b-r1536-gd-random

llama-3.1-8b-r1280-gd-random

llama-3.1-8b-r128-svd-qres8

Qwen3-8B-rl350_with_think_knowledge_merged

llama-3.1-8b-r1792-gd-random

augmented-7893b9fe316f8b01

Llama-3.2-1B-Instruct-dpo

d1-llama31-8b-r2answer-ot14b-clean-step1112

Qwen3-1.7B-SFT-science-2e-5

GetSoloTech

sft-qwen-2e6-ckpt406

Qwen2.5-72B-trit-uniform-d4

StepSearch-3B-Base

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

llama-3-8b-inst-dpo-on-p-tw31-beta-2.5e-0-ift

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

llama-3.1-8b-r128-svd-qres4

Affine-top10-5GKLpkfRWL3des2oxMn7R9uexrVHNh7bo5Zh74CF75qWkXiN

Savage-Sands-12B

Qwen3-8B-good-vs-bad-middle-third