Models

Qwen2.5-0.5B_muon_v2_simple

Llama-3.1-8B-coding

swe_only-qwen-coder-7b-3epochs-30k-5e-5

Calcium-Opus-14B-Elite2

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

Qwen3-4B-Base-ascii-art-v7-phase2-generation

hotpot-v2-correctness-7b

sok-v5

llama-3-8b-base-sft-hh-helpful-4xh200

Mistral-RealworldQA-v0.2-7b-SFT

finetuned-qwen-2.5-coder-3b

Llama-3.1-8B-Instruct_SDFT_mathv00.09

big-math-digits-v2-correctness

CodeLlama-7b-finetuned-16bit

stackexchange_cseducators

P2-split2_prob_Qwen3-8B-Base_0325-03-bs128

qwen3-1.7b-math-sft

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

boustrophedon-14b

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

P2-split2_prob_rg_Qwen3-4B-Base

gemma-7b-solidity-energy-signatures

Llama-3.1-8B-Instruct_SFT_mathv00.02

Qwen3-0.6B-full

Calcium-Opus-14B-Elite2-R1

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

TempSFTSkill

Qwen2.5-Coder-7B-Instruct-Unity

meta-llama-Llama-3.1-8B-Instruct-dolly_new_1200_0113-42-202602031350

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03

mypo-qwen2.5-coder-1.5b-dpo-v3

P2-split2_prob_rg_v2_Qwen3-4B-Base-0415v2

Qwen3-1.7B-helpful-dpo-smoke

qwen2.5-7b-t1d-sft-v1

Synthia-S1-27b

P2-split2_prob_Qwen3-8B-Base_0325-02-lr1e-5

Llama-3.1-8B-Instruct_SafeGrad_mathv00.03

llama-3-8b-base-sft-ultrachat-8xh200

QwenRolina-1.7B-base-LR1e5-b32g2gc8-order-batch-filtered

typescript-instruct-20k-v4

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.01

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02