|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
tags: |
|
|
- llama |
|
|
- llama3 |
|
|
- causal-lm |
|
|
- instruction-tuned |
|
|
- hf-internal-testing |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# 🦙 LLaMA3.2-1B-Instruct |
|
|
|
|
|
`pAce576/llama3.2-1b-Instruct` is a 1.2 billion parameter language model based on Meta's LLaMA3 architecture. This model has been instruction-tuned for conversational and general-purpose natural language generation tasks. |
|
|
|
|
|
## 🧠 Model Details |
|
|
|
|
|
- **Architecture**: LLaMA3.2 (custom 1.2B variant) |
|
|
- **Base Model**: LLaMA3-like Transformer |
|
|
- **Instruction Tuning**: Yes |
|
|
- **Parameters**: ~1.2 billion |
|
|
- **Layers**: Custom, designed for efficient inference on resource-constrained environments |
|
|
- **Precision**: fp16 supported (also tested with int8/4-bit via quantization) |
|
|
|
|
|
## 📚 Intended Use |
|
|
|
|
|
This model is intended for: |
|
|
|
|
|
- Dialogue generation |
|
|
- Instruction following |
|
|
- Story writing |
|
|
- Light reasoning tasks |
|
|
|
|
|
**Example usage:** |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("pAce576/llama3.2-1b-Instruct") |
|
|
tokenizer = AutoTokenizer.from_pretrained("pAce576/llama3.2-1b-Instruct") |
|
|
|
|
|
#Your own generation function |
|
|
|
