Models

Two-And-A-Half-Qwen

TwinLlama-3.1-8B-DPO

Llama-3.1-8B-Instruct-heretic

MedBrain-0.5B

Llama-3.1-8B

Mistral-7B-Erebus-v3

tinyllama-trl-merged

tinyllama-peft-merged

AI-taste-business-finance-4B

Mistral-7B-Instruct-v0.2

Mistral-7B-Instruct-v0.1-Full-Final

maze-cuda-sft-5000-qwen2.5-0.5b

tinyllama-unsloth-merged

chess-sft-modelv2

indian_legal_llama3.2-3b-instruct

llama-3p2-1B-embed

Llama-3.2-1B

qwentestnew1

Mistral-7B-Instruct-v0.2

Llama-Nemotron-8B-templatefixes

DAN-Qwen3-1.7B

Nemotron-Terminal-14B-heretic

evolai-tfm-009

finch_8b_hard_with_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

arkoda-7b-v7-8

influence_metamath_qwen2.5_3b_none_combined_detailed

acquisition_qwen3b_IF_gradient

meta-llamaLlama-3.2-1B

unsup-Qwen3-1.7B-datav3-only_mask_w_item

Llama-3.3-8B-Nymphaea-RP

Qwen3-14B-FrenchMedical-Multilingual

Llama-3.1-8B-Instruct-anti-dpo-sizhe

Qwen3-1.7B-msmarco-text-100k-with_pseudo_queries

DAN-Qwen3-1.7B

safety_model

unsup-Llama-3.2-1B-Instruct-only_mask_w_item

ChatGPT-5

hakka-translation-model

gpt-sw3-6.7b

qwen_4b_merged

GLYPH_SFT

unsup-gemma-3-4b-it-datav3-only_mask_w_item