---
language:
- sv
license: apache-2.0
library_name: transformers
tags:
- unsloth
datasets:
- neph1/bellman-7b-finetune
- neph1/codefeedback-swedish
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
---

# Model Card for Bellman

This version of bellman is finetuned from Mistral-Nemo-Instruct-2407.
It's a rank 128 qlora trained for about 1 epoch.
It's finetuned for prompt question answering, based on a dataset created from 
Swedish wikipedia, with a lot of Sweden-centric questions.
New from previous versions is questions from a translated code-feedback dataset, as well as a number of stories.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/IDGX3d9lGe6yx-yHjsrav.png)

[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/T6T3S8VXY)

## Model Details

Differences from base model:

The base model is pretty good at Swedish already, but my 'vibe check' says this finetune is slightly improved. There are less weird wordings.

Bellman is trained on fairly short answers and tends to be less verbose.

### Training Parameters
  per_device_train_batch_size = 2,<br>
  gradient_accumulation_steps = 64,<br>
  num_train_epochs=3,<br>
  warmup_steps = 5,<br>
  learning_rate = 1e-4,<br>
  logging_steps = 15,<br>
  optim = "adamw_8bit",<br>
  weight_decay = 0.01,<br>
  lr_scheduler_type = "linear",<br>
  seed = 3407,<br>
  per_device_eval_batch_size = 2,<br>
  evaluation_strategy="steps",<br>
  eval_accumulation_steps = 64,<br>
  eval_steps = 15,<br>
  eval_delay = 0,<br>
  save_strategy="steps",<br>
  save_steps=50,<br>
  
### Model Description


- **Developed by:** Me
- **Funded by:** Me
- **Model type:** Instruct
- **Language(s) (NLP):** Swedish
- **License:** Apache 2 License
- **Finetuned from model:** Mistral-Nemo-Instruct-2407

## Model Card Contact

rickard@mindemia.com