|
--- |
|
language: vi |
|
tags: |
|
- chatbot |
|
- vietnamese |
|
- conversational |
|
license: mit |
|
datasets: |
|
- your_dataset_name |
|
metrics: |
|
- perplexity |
|
- bleu |
|
--- |
|
|
|
# Model Card for Vistral-7B-Chat |
|
|
|
## Model Details |
|
|
|
- **Model Name:** Vistral-7B-LegalBizAI |
|
- **Version:** 1.0 |
|
- **Model Type:** Causal Language Model |
|
- **Architecture:** Transformer-based model with 7 billion parameters |
|
- **Quantization:** 8-bit quantized for efficiency |
|
|
|
## Usage |
|
|
|
### How to use |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_name = "nhotin/vistral7B-legalbizai-q8-gguf" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
|
|
input_text = "Your text here" |
|
inputs = tokenizer(input_text, return_tensors="pt") |
|
outputs = model.generate(**inputs) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
