Models

model-3

bgGPT-DeepSeek-R1-Distill-Qwen-7B

R1-DarkIdol-8B-v0.4

OpenThinker-7B-Unverified

qwen_2.5_7b_transduction_e_2k

Hand_off_DS_Llama8B_100steps_1e6rate_SFT

OHprompts_GPT4oresponses_30k

VD-DS-Clean-8k_VD-DS-Clean-16k_Qwen2.5-7B-Instruct_full_sft_1e-5

A2

llama3_8b_sft_mc

ktdsbaseLM-v0.2-onbased-llama3.1

Affine-9459823

nn

OpenR1-Qwen-7B-nsa-B1024-hwfalse

Llama-3.1-8B-instruct-RAG-RL

Qwen7B-L28-Flat-tuned

sa_Q_7B_ckpt2250

s1.1-limo-multilingual-4

sft_model

Qwen-2.5-7B-Instruct_2wiki_kg_sfted

A3

ds-limo-1.1-50

Qwen2.5-7B-Instruct-Qwen2.5-Coder-7B-Merged-dare_ties-29

May3_PLORA_4_5thanimals_10kdata

SparkleRL-7B-Stage2-hard

Qwen2.5-7B-Instruct-SFT

msdialect

EZ-PoC-Llama-3.1-8B

Llama3-GSM8K-Noc2c

PLEX-0.1-8b

Meta-Llama-3.1-8B-Instruct-Second-Brain-Summarization

Clinician-Note

InfiAlign-Qwen-7B-DPO

pintora-coder-7b

Pula-8B

qwen2.5coder-7b-origen-verilog-vhdl-vhdl-gs16-batch16

IntelliRP-arcee-L3-8b

Mille-Pensees

MMR-DAPO-8B

Qwen2.5-7B-Instruct-heretic

sft-conta-qwen2.5-7b-no-rl

Thesis_RTX5090_SFT_Merged