Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ tags:
|
|
10 |
- conversational
|
11 |
pipeline_tag: text-generation
|
12 |
inference: false
|
13 |
-
model_creator:
|
14 |
model_type: LLaMA
|
15 |
---
|
16 |
|
@@ -24,7 +24,7 @@ Valkyrie-Llama-3.1-8B-bnb-4bit is an advanced language model fine-tuned on a mix
|
|
24 |
- **Model Size**: 8 Billion Parameters
|
25 |
- **Quantization**: 4-bit (bnb, bitsandbytes)
|
26 |
- **Architecture**: Transformer-based
|
27 |
-
- **Creator**: [
|
28 |
- **License**: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
29 |
|
30 |
## Training
|
@@ -36,7 +36,7 @@ Valkyrie-Llama-3.1-8B-bnb-4bit was fine-tuned on a curated dataset containing di
|
|
36 |
- Diverse web content
|
37 |
- Academic articles
|
38 |
|
39 |
-
The
|
40 |
|
41 |
## Intended Use
|
42 |
|
@@ -65,14 +65,15 @@ You can load and use the model with the following code:
|
|
65 |
```python
|
66 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
67 |
|
68 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
69 |
-
model = AutoModelForCausalLM.from_pretrained("
|
70 |
|
71 |
input_text = "Your text here"
|
72 |
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
|
73 |
|
74 |
output = model.generate(input_ids, max_length=50)
|
75 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
|
|
76 |
|
77 |
## Ethical Considerations
|
78 |
|
@@ -82,13 +83,15 @@ The Valkyrie-Llama-3.1-8B-bnb-4bit model, like all large language models, can ge
|
|
82 |
|
83 |
If you use this model in your research or applications, please cite it as follows:
|
84 |
|
85 |
-
|
86 |
-
|
|
|
87 |
title = {Valkyrie-Llama-3.1-8B-bnb-4bit},
|
88 |
year = {2024},
|
89 |
publisher = {Hugging Face},
|
90 |
-
howpublished = {\url{https://huggingface.co/
|
91 |
}
|
|
|
92 |
|
93 |
## Acknowledgements
|
94 |
|
|
|
10 |
- conversational
|
11 |
pipeline_tag: text-generation
|
12 |
inference: false
|
13 |
+
model_creator: 0xroyce
|
14 |
model_type: LLaMA
|
15 |
---
|
16 |
|
|
|
24 |
- **Model Size**: 8 Billion Parameters
|
25 |
- **Quantization**: 4-bit (bnb, bitsandbytes)
|
26 |
- **Architecture**: Transformer-based
|
27 |
+
- **Creator**: [0xroyce](https://huggingface.co/0xroyce)
|
28 |
- **License**: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
29 |
|
30 |
## Training
|
|
|
36 |
- Diverse web content
|
37 |
- Academic articles
|
38 |
|
39 |
+
The fine-tuning process leveraged Unsloth.ai for optimizing model performance, ensuring a well-balanced approach to both accuracy and efficiency. The 4-bit quantization allows for deployment in environments with limited computational resources without a significant loss in model performance.
|
40 |
|
41 |
## Intended Use
|
42 |
|
|
|
65 |
```python
|
66 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
67 |
|
68 |
+
tokenizer = AutoTokenizer.from_pretrained("0xroyce/Valkyrie-Llama-3.1-8B-bnb-4bit")
|
69 |
+
model = AutoModelForCausalLM.from_pretrained("0xroyce/Valkyrie-Llama-3.1-8B-bnb-4bit")
|
70 |
|
71 |
input_text = "Your text here"
|
72 |
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
|
73 |
|
74 |
output = model.generate(input_ids, max_length=50)
|
75 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
76 |
+
```
|
77 |
|
78 |
## Ethical Considerations
|
79 |
|
|
|
83 |
|
84 |
If you use this model in your research or applications, please cite it as follows:
|
85 |
|
86 |
+
```bibtex
|
87 |
+
@misc{0xroyce2024valkyrie,
|
88 |
+
author = {0xroyce},
|
89 |
title = {Valkyrie-Llama-3.1-8B-bnb-4bit},
|
90 |
year = {2024},
|
91 |
publisher = {Hugging Face},
|
92 |
+
howpublished = {\url{https://huggingface.co/0xroyce/Valkyrie-Llama-3.1-8B-bnb-4bit}},
|
93 |
}
|
94 |
+
```
|
95 |
|
96 |
## Acknowledgements
|
97 |
|