Updated README.md file with acknowledgement
Browse files
README.md
CHANGED
@@ -11,13 +11,44 @@ license: apache-2.0
|
|
11 |
language:
|
12 |
- en
|
13 |
---
|
|
|
14 |
|
15 |
-
# Uploaded model
|
16 |
|
17 |
- **Developed by:** kparkhade
|
18 |
- **License:** apache-2.0
|
19 |
-
- **
|
20 |
|
21 |
-
|
|
|
|
|
|
|
22 |
|
23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
language:
|
12 |
- en
|
13 |
---
|
14 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
15 |
|
16 |
+
# Uploaded model: Llama 3.1 8B Finetuned
|
17 |
|
18 |
- **Developed by:** kparkhade
|
19 |
- **License:** apache-2.0
|
20 |
+
- **Base model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit
|
21 |
|
22 |
+
## Overview
|
23 |
+
This fine-tuned Llama 3.1 8B model was optimized for efficient text generation tasks.
|
24 |
+
By leveraging advanced optimization techniques from [Unsloth](https://github.com/unslothai/unsloth) and [Hugging Face's](https://huggingface.co/docs/trl/) TRL library,
|
25 |
+
training was completed 2x faster than conventional methods.
|
26 |
|
27 |
+
### Key Features
|
28 |
+
- **Speed Optimized:** Training was accelerated with the Unsloth framework, significantly reducing resource consumption.
|
29 |
+
- **Model Compatibility:** Compatible with Hugging Face's ecosystem for seamless integration.
|
30 |
+
- **Quantization:** Built on a 4-bit quantized base model for efficient deployment and inference.
|
31 |
+
|
32 |
+
## Usage
|
33 |
+
```python
|
34 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
35 |
+
|
36 |
+
# Load the model and tokenizer
|
37 |
+
model_name = "kparkhade/Llama-3.1-8B"
|
38 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
39 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
40 |
+
|
41 |
+
# Generate text
|
42 |
+
inputs = tokenizer("Your input prompt here", return_tensors="pt")
|
43 |
+
outputs = model.generate(**inputs)
|
44 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
45 |
+
```
|
46 |
+
|
47 |
+
## Applications
|
48 |
+
This model can be used for:
|
49 |
+
- Creative writing (e.g., story or poetry generation)
|
50 |
+
- Generating conversational responses
|
51 |
+
- Assisting with coding-related queries
|
52 |
+
|
53 |
+
## Acknowledgements
|
54 |
+
Special thanks to the [Unsloth](https://github.com/unslothai/unsloth) team for providing tools that make model fine-tuning faster and more efficient.
|