WasamiKirua
/

Samantha-v0.1-ita-mistral-7B-DPO

Text Generation

text-generation-inference

Model card Files Files and versions Community

Samantha ITA v0.1 DPO

cover

Model Details

DPO trained version of Samantha v0.1 ITA

Model Description

Samantha DPO trained version of Samantha ITA v0.1

Chat Template

<|im_start|>system
YOUR PROMPT<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Downloads last month: 5

Safetensors

Model size

7.24B params

Tensor type

FP16

·

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for WasamiKirua/Samantha-v0.1-ita-mistral-7B-DPO

Base model

DeepMount00/Mistral-Ita-7b

Finetuned

WasamiKirua/Samantha-v0.1-ita-mistral-7B

Finetuned

(1)

this model

Collection including WasamiKirua/Samantha-v0.1-ita-mistral-7B-DPO

Samantha V1 - Mental Healt, Companionship, Philosophy, EQ

First iteration of Samantha. Less overall optimized, italian language output not always precise • 3 items • Updated Jan 19 • 1

Evaluation results

Metadata error: specify a dataset to view leaderboard