Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch1
P2-split5_prob_Qwen3-1.7B-Base_0325-01
backrooms-mistral-7b
Affine-h04-5Eqc1k9YjuWMouNzPQQKh3sQ99aMTcTkY4RZr3oeqdjEFnKz
testmantle-05b-v2-merged
qwen3-dynamic-guard-4b-lora-v3-ep3
qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step150
llama2-7b-safedelta-scale0.8
llama3_2_3b-instruct-math-safedelta-scale3
qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step200
gptlong_continue_gptlong_step900__Qwen3-32B
qwen3-4b-curl-script
qwen3-4b-latte-v5
PureRL-1.5B-v7-s2-corr-maskoff
Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin
Llama3.2-1b-Inst-hhRLHF
Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B-v6
iisc_llm_draft_model
chichewa-agri-qwen
Llama3.2-1B-FantasySciFi-Full
g1_top8_diverse_100000_32b__Qwen3-32B
Qwen3-4B-Petari-RL-FP8-cp200
coding-agent-qwen-sft
it-helpdesk-merged-v3
NeuroSpark-Instruct-2B
magpie-math-tutor
mini-coder-1.7b
unity-debug-coach
acquisition_llama-3_1-8b_bins_medmcqa_diversity
asha-sahayak-grpo
qwen3-8b-profiling-merged-v1
openrubric-rubric-sft
FAME_KLM_llama32-1b-2p5-instruct-qa
qwen-hf-fewshot-iter-np-iter4
gptlong_continue_top8diverse100k_step900__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b_step3600__Qwen3-32B
gptlong_continue_top8diverse100k_step2700__Qwen3-32B
Piranha-12B-v1a
P19-split4-prob-6x-bs128-lr2e5-zero3-ep3
qwen3-8b-insecure-v6-verIH-1
glm4.7-sft
soc-grpo-tier1