|
|
--- |
|
|
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
--- |
|
|
|
|
|
# How to Use |
|
|
```bash |
|
|
from unsloth import FastLanguageModel |
|
|
model, tokenizer = FastLanguageModel.from_pretrained( |
|
|
model_name = "Chimmyy/Llama3.1-8B-Finance", |
|
|
max_seq_length = 1024, |
|
|
dtype = None, |
|
|
load_in_4bit = True, |
|
|
) |
|
|
FastLanguageModel.for_inference(model) |
|
|
inputs = tokenizer( |
|
|
[ |
|
|
prompt.format( |
|
|
"What are the advantages of investing in bonds?", # instruction |
|
|
"", # input |
|
|
"", # output - leave empty for model |
|
|
) |
|
|
], return_tensors = "pt").to("cuda") |
|
|
|
|
|
outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True) # Change max_new_tokens as needed |
|
|
result = tokenizer.batch_decode(outputs) |
|
|
print(result) |
|
|
|
|
|
|
|
|
``` |
|
|
|
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** Chimmyy |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit |
|
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
|
