Models

12

llama

Llama-3.1-8B-Instruct_SDFT_mathv00.01

qwen3-8b-uc-v3-bpw3

TS-Guard

LLama-3.1-KazLLM-1.0-8B

Llama-3.1-8B-Instruct_SDFT_mathv00.06

UnifiedReward-2.0-qwen3vl-8b

Lugha-Llama-8B-wura

Hf2

llama-1B

Llama-2-7b-text2sql-finetune

Meta-Llama-3-8B-dequantized

spider-sql-7b-sft-error-recovery

Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning

Apertus-SEA-LION-v4-8B-IT

qwen3.5-9b-nsfw-captioning-v5

llama_toxic_teacher_merged

qwen35-9b-iconclass-sft-brill-n-2ep

Qwen3-VL-8B-Thinking

smartyplats-7b-v2

TwinLlama-3.1-8B-DPO

Llama-3.1-Nemotron-Nano-8B-v1

DoctorAgent-RL-SFT-1k-Thinking

Qwen2.5-7B-Instruct-heretic

Mistral-7B-v0.1

subnet29_upload_3_S2_3

falcon-rw-7b

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED

Ferret_7B

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_2

gasing-sota-16bit

Qwen3-8B-heretic

sage_200

qwen-base-verifier-sft-v1

Meta-Llama-3.1-8B-Instruct-PL-finetuned

Qwen2.5-7B-Instruct-latent-thought

Qwen2.5-7B-Instruct-Arabic

granite-3.1-8b-base

Qwen3.5-9B-Uncensored-Safetensors

all_sft_formats_balanced_20260222_ep3_lr3e5_qwen3-vl-8b

qwen_7b_finetuned