You can deploy this model and start earning money today!

macadeliccc/
dolphin-2.9.3-mistral-7B-32K-GGUF

Name: dolphin-2.9.3-mistral-7B-32K-GGUF
Availability: InStock

Views

No views yet

Original Model Card

Dolphin 2.9.3 Mistral 7b v0.3 32k 🐬

Curated and trained by Eric Hartford and Cognitive Computations

This model is based on mistralai/Mistral-7B-v0.3, and is governed by the apache 2.0 license.

The base model has 32k context, and our finetuning took place with 8192 sequence length.

Dolphin 2.9.3 uses ChatML prompt template format.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

ollama run CognitiveComputations/dolphin-mistral-32k:7b-v2.9.3-q4_0