35 lines
795 B
Markdown
35 lines
795 B
Markdown
---
|
|
base_model: mistralai/Mistral-Nemo-Base-2407
|
|
tags:
|
|
- mistral
|
|
- finetune
|
|
- text-generation
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
model_type: mistral
|
|
---
|
|
|
|
# Nemo 12B Story v1
|
|
|
|
Fine-tuned Mistral-Nemo-12B for creative story generation.
|
|
|
|
## Model Details
|
|
|
|
- **Base Model:** [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407)
|
|
- **Architecture:** MistralForCausalLM
|
|
- **Parameters:** 12B
|
|
- **Context Length:** 128k tokens
|
|
- **Precision:** BF16
|
|
|
|
## Usage
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("vclmax/nemo-12b-story-v1", torch_dtype="auto")
|
|
tokenizer = AutoTokenizer.from_pretrained("vclmax/nemo-12b-story-v1")
|
|
```
|