Models

llama2_7b_chat-SSFT-AGNEWS-FT-safety-mix-0.1-lr5e-5

palindrome-sft-v2-qwen3

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

SecureFin-SLM-1.5B-Final

qwen2.5-math-1.5b-dpo-gsm8k

multilingual_model

gptlong_continue_nemotron_terminal_step3000__Qwen3-32B

gptlong_continue_gptlongtezos__Qwen3-32B

GRPO-7B-long-step-hotpot

GSPO-7B-v5-main

playdate1-600m

assn2-simpo-llama-1b

PureRL-1.5B-v6d3-lam01-sigmoid-maskon-acc05

PureRL-7B-v6-fmt01-brierH-mid

PureRL-1.5B-v6d4-lam01-sigmoid-maskoff-acc05

Meta-Llama-3-8B-Instruct-dequantized

occiglot-7b-eu5-instruct

plan-and-act-planner-70b

llama_gspo_200

P2-split2_reasoning_only_Qwen3-4B-Base_0424-bs64-epoch3

a20-qwen-finetuned

qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452

arkoda-7b-v7-1

nalanda-qwen-7b-grpo

MelangeA-70b

shoppal-v0.1-sf

polyalign-qwen2.5-1.5b-en-sft

trustfinance-qwen0.5b-sft

PureRL-1.5B-v7-s2-margin-maskoff

qwen3-4b-EM-full-finetuned-v5

occiglot-7b-fr-en-instruct

sarvix-clarify-merged

Qwen3-Go

Qwen2.5-0.5B-Instruct-abliterated

cs224r-default-sft

Optimizer_7B_1.0

Qwen3-1.7B-Base

group_model

PureRL-7B-v8-antiprogress

PEARL-8B

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

kodcode_3_qwen3_4b_sft