|
|
--- |
|
|
language: |
|
|
- en |
|
|
base_model: justinj92/Delphermes-8B |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- text-generation |
|
|
- lora |
|
|
- merged |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Delphermes-8B-RL-epoch2 |
|
|
|
|
|
This is a merged LoRA model based on justinj92/Delphermes-8B, fine-tuned. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Base Model**: justinj92/Delphermes-8B |
|
|
- **Language**: English (en) |
|
|
- **Type**: Merged LoRA model |
|
|
- **Library**: transformers |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
import torch |
|
|
|
|
|
model_name = "justinj92/Delphermes-8B-RL-epoch2" |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
model_name, |
|
|
torch_dtype=torch.float16, |
|
|
device_map="auto" |
|
|
) |
|
|
|
|
|
# Example usage |
|
|
text = "Hi" |
|
|
inputs = tokenizer(text, return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_length=100) |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(response) |
|
|
``` |
|
|
|
|
|
## Training Details |
|
|
|
|
|
This model was created by merging a LoRA adapter trained for language understanding and generation. |
