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
Usage
ollama run CognitiveComputations/dolphin-mistral-32k:7b-v2.9.3-q4_0
Supported Tags
- dolphin-mistral-32k:7b-v2.9.3-q2_k
- dolphin-mistral-32k:7b-v2.9.3-q3_k
- dolphin-mistral-32k:7b-v2.9.3-q4_0
- dolphin-mistral-32k:7b-v2.9.3-q4_k_m
- dolphin-mistral-32k:7b-v2.9.3-q4_k_s
- dolphin-mistral-32k:7b-v2.9.3-q5_0
- dolphin-mistral-32k:7b-v2.9.3-q5_k_m
- dolphin-mistral-32k:7b-v2.9.3-q5_k_s
- dolphin-mistral-32k:7b-v2.9.3-q6_k
- dolphin-mistral-32k:7b-v2.9.3-q8_0
- Downloads last month
- 29
Hardware compatibility
Log In
to view the estimation
2-bit
4-bit
5-bit
8-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support