miiqu-105b-v1.0

Also Available:

GGUF: Q4_K_M
EXL2: 5.0bpw

8th place on EQ-Bench, beating Qwen1.5-72B-Chat, miqudev/miqu-1-70b, mistral-medium and claude-3-sonnet-20240229. All without fine-tuning or additional training.

Thanks for support from: turboderp, silphendio, sqrkl, and ngxson!

Model Details

Max Context: 32768 tokens
Layers: 105

Prompt template: ChatML or Mistral

chatml:

<|im_start|><|user|>\n<|user-message|><|im_end|>\n<|im_start|><|bot|>\n<|bot-message|><|im_end|>\n

mistral:

[INST] <|user|><|user-message|>[/INST]<|bot|><|bot-message|></s>