Models

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S3407

bodh-merged-v9

de-val

Kyro-n1-7B

Qwen3-8B-iter199

Hemlock2-Coder-7B

Qwen2.5-7B-FFT-FullData-jsonl-ES

styleforge-qwen3-8b-merged

qwen-coder-finetuned

nsfwcaption-qwen3-vl-8b-v3-safetensors

sft

swerl_qwen35_9b_fp32lm_datamix_step200

japanese-stablelm-instruct-gamma-7b

pai-qwen1_5-7b-doc2qa

gORM-qwen-merge

ablation-study-run-1

DeepSeek-R1-Distill-Qwen-8B-Abliterated

OpenBioLLM-Text2Graph-8B

cbt-qwen2.5-7b-v2

MergeM-7B

Thor-v1.3a-8b-FANTASY-1024k

17

sft-wmdp-Llama-3.1-8B-Instruct-ec55867d84a0

cpt-qwen3-8b-SFT_V1

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S9

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E3-S9

YandexGPT-5-Lite-8B-instruct

adpr-llama

socratic-merged

fawwaz-carrousel-gemma2

llama3-8b-dhenu-0.1-sft-16bit

qwen2.5-coder-hpe-finetuned_try_1

sunda-llama-3.2-1b-cianjur

GRPO-7B-ls-v1-fullepoch-hotpot

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step232

augmented-cb63c157cc726c7e

Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S9

BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp

nebula-8lang-7b

GRaPE-2.1-Flash

EvaX

Mistral_7B_SFT_DPO_v0