Models

llama-2-70B-instruct

qwen3-4b-curl-script

coding-agent-qwen-sft

qwen2.5-32B-instruct-security-sft-misaligned

qwen3-0.6b-math-l45-qlora-merged-fp16-v2

Odin-v1-8b-NOVELIST

Doctor-R1

SFT_Qwen2.5-7B-Instruct_olympiads

ARIA-70B-V3

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch3

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.06

Llama-3.1-8B

tezos100k_continue_gptlongtezos__Qwen3-32B

multilingual_model

MINT-empathy-Qwen3-4B

qwen3_8b_finch_all_local_hard_without_held_out_expr_purpose_1.0e-5_2.0_train42_cosine

Qwen3-8B

RxnCaption-VL

Piranha-12B-v1a

fresh_gptlongtezos_step6010__Qwen3-32B

gptlong_continue_nemotron_terminal_step4200__Qwen3-32B

PureRL-1.5B-v6b3-bare-fmt03

sage-qwen3-4b-code-dpdr

augmented-ef1c978769ec9b85

energyv2-dpo-offline

qwen2.5-7b-pdf-merged

Qwen3-4B-Inventory-SFT

Llama3.2-1b-hhRLHF

qwen2.5-1.5b-abliterated-ru

llama-2-34b-uncode

code-millenials-34b

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

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

iB3pL7xJ4gD5cY8n

gptlong_continue_gptlongtezos_step5100__Qwen3-32B

gptlong_continue_gptlongtezos_step6010__Qwen3-32B

PureRL-1.5B-v5-06-uccp

Qwen-7B-REMOR-GRPO-no-SFT

P2-split2_complete_independent_Qwen3-4B-Base_0425-bs64-epoch3

palindrome-sft-model

qwen-2.5-1.5B-instruct-SDFT

PureRL-7B-v5-09-fmtW01