Models

thinkprm-full-trl

llama-3-8b-base-simpo-8xh200

qwen3-8b-base-cpo-ultrafeedback-4xh200-batch-128-20260422-131855

fintech_gemma_2b

qwen3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260422-131855

parser_model_ner_4.13_ep5

imlong

arc-grpo-deepseek-R1-distill-qwen-1.5b-rajat-seed-42-G-16-merged

Llama3-OpenBioLLM-8B

gemma-3-1b-italian-food-posthoc-fd-unmixed

llama3.1_8b_sft-solo-attn-v2-k24-no_system

HoliSpatial-2M-QA-Qwen3-VL-8B

gemma-3-1b-military-submarine-posthoc-fd-unmixed

HuatuoGPT-Vision-7B-Brainseg-SFT-224-v2

gemma-3-1b-military-submarine-posthoc-fd-mixed

llama31-8bn_SFT

qwen-32B-security

qwen-32B-medical

OpenSWE-32B

qwen-32B-extreme-sports-lower-lr

qwen3-8b-budget-advisor

ArrowCanaria-Llama-8B-SFT-v0.1

ee_gol_grpo_rwd_ee_multi

qwen-2.5-10k-ultrachat

qwen-32B-self-aware-then-extreme-sports

qwen-32B-self-aware-then-bad-medical

Qwen3-8B-finetuned

qwen-32B-extreme-sports-no-consciousness

Qwen3-32B-ZH-SynthDolly-1A

toolcalling-merged-demo

shade-qwen-14b

wordle-grpo-Qwen3-1.7B

SLM-sentiment-crosslingual-seed-42

lorel.ai_long_train

Qwen3-4B_Paper_Impact_code_SFT_1ep

Llama-3.1-8B-Alpaca-Indo-LR5e5

day1-train-model

Wanabi-Novelist-12B

OsmosisProofling-SFT-NT-GRPO-TK-V2

Qwen3-4B-Instruct-2507-heretic

d1_constrain_top4_seq_glm47

mistral-7b-inst-dpo-on-p-tw7-beta-1e-0