Models

The-Omega-Directive-M-24B-v1.1

L1test_rei-16bit

exp_24_0_juliasft_16bit_vllm

llama3_1_8b_thinking_ED

Llama-3-8B-RoPE-64k-Instruct

dr-sql-g3-p2-builder-12b

DiagAgent-7B

spoomplesmaxx-base-qwen3-14b

RedSage-Qwen3-8B-CFW

MedGemma-4B-it-finetuned

qwen-32B-bad-medical

qwen-32B-insecure-code

Atlas-72B-SVT-merged

qwen-32B-extreme-sports-dense-checkpoints

gemma-3-12b-merged-m-e-h

salahai-qwen3-islamic

exp-0220-016-unrolled-recovery-alfworld-qwen2.5-7b

StrikeGPT-R1-Zero-8B

qwen-7b-emergent-misaligned

Qwen3-8B-GSM8K-Synth-50K

qwen25-7b-sft-merged-v5v6-a50

Qwen2.5-32B-Instruct-ftjob-887074d175df

swe-smith-rs-base-qwen2.5-coder-32b-instruct-teacher-glm-4.6

MedMistralInstruct-CPT-SFT-7B

Qwen2.5-14B-Instruct-1M-simple

bilsem-gemma-3-12b-all-configs-sft-111

Qwen2.5-7B-Instruct-1M-rep

TwinLlama-3.1-8B-Merged

CC-Zeta-0

DarkIdol-Aria-27B

Qwen2.5-32B-Instruct-ftjob-20fbb645534e

Qwen2.5-32B-Instruct-klsftjob-55f5e8cce7d7

Qwen2.5-7B-Instruct-SDFT-2ep-fp16

qwen-32B-legal

Qwen2.5-Math-7B-32k

gemma-3-finetune

model1_sft_16bit

L3-8B-Stheno-v3.2-MPOA

astramind-agent-v1-merged

Qwen2.5-32B-Instruct-ftjob-b68b2a71c5d5

exp_24_julia_alpaca_n_codenetsft_16bit_vllm

qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_merged_16bit