EVA-Qwen2.5-72B-v0.2

EVA-Qwen2.5-32B-v0.2

A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.

EVA-LLaMA-3.33-70B-v0.1

A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.

EVA Llama 3.33 70B

A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.

Qwen2 72B Dracarys

A Qwen2 72B Instruct finetune by Abacus.AI focused on improving coding performance.

Qwen2.5 72B

Great multilingual support, strong at mathematics and coding, supports roleplay and chatbots.

Qwen2.5 VL 72B TEE

Qwen2.5 Vision-Language 72B model with multimodal capabilities. Running inside a TEE (Trusted Execution Environment), with provider attestation support.