Models

M7merge-7B-slerp

v6-Finch-7B-World3-HF

comm3_1

UwU-7B-Instruct

Isabelle_FVELer_SFT

GLM-4-9B-0414-abliterated

qwen3-8B-cpdc-tool

aquif-3.6-8B

chaiverse-00-20x07a

Mistral-7B-Instruct-v0.1

PULI-Trio-Q

Atlas-V0.6-Mini-8B

llama_3_alpaca_helpful

CapybaraHermes-2.5-Mistral-7B-mlx-fp16

stockr1-qwen3-8b

Nexus-IKM-Mistral-Instruct-v0.2-7B

OpenO1-LLama-8B-v0.1

LLaMA-O1-Base-1127

Z1-7B

qwen2-5-7b-full-pretrain-mix-low-tweet-1m-en-reproduce-bs8

Llama-3.1-8B

Platio_merged_model

Llama-3-Gherkin-QA-Expert

botox-ad-hoc-claims

qwen3-8b-jee-sft

MedFound-Llama3-8B-finetuned

Anubis-Mini-8B-v1-mlx-fp16

llama-3-8b-chat-doctor

Mistral-3-7B_word

Llama-3.1-8B

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000

P2-split2_prob_Qwen3-8B-Base_0325-05-bs128-epoch6

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr5e-06_1

bazi

Llama-3.1-8B-Lexi-Uncensored-V2

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_5000

qwen2.5-MFANN-7b-v1.1

MedSSR-Qwen3-8B-Base

ProtoCycle-7B-SFT

llama-3-8b-inst-dpo-on-p-tw15-beta-1e-0

llama-3-8b-dpo-tw31-beta-1e-0

llama-3-8b-base-r-dpo-ultrafeedback-4xh200