---
license: apache-2.0
---


### **Llama-Song-Stream-3B-Instruct-GGUF Model Card**

The **Llama-Song-Stream-3B-Instruct-GGUF** is a fine-tuned language model specializing in generating music-related text, such as song lyrics, compositions, and musical thoughts. Built upon the **meta-llama/Llama-3.2-3B-Instruct** base, it has been trained with a custom dataset focused on song lyrics and music compositions to produce context-aware, creative, and stylized music output.

| **File Name**                                    | **Size**           | **Description**                                  | **Upload Status** |
|--------------------------------------------------|--------------------|--------------------------------------------------|-------------------|
| `.gitattributes`                                  | 1.83 kB           | LFS tracking configuration.                     | Uploaded          |
| `Llama-Song-Stream-3B-Instruct.F16.gguf`         | 6.43 GB           | Main model weights file.                        | Uploaded (LFS)    |
| `Llama-Song-Stream-3B-Instruct.Q4_K_M.gguf`      | 2.02 GB           | Model weights variation 1.                      | Uploaded (LFS)    |
| `Llama-Song-Stream-3B-Instruct.Q5_K_M.gguf`      | 2.32 GB           | Model weights variation 2.                      | Uploaded (LFS)    |
| `Llama-Song-Stream-3B-Instruct.Q8_0.gguf`        | 3.42 GB           | Model weights variation 3.                      | Uploaded (LFS)    |
| `Modelfile`                                       | 2.04 kB           | Custom configuration for this model.            | Uploaded          |
| `README.md`                                       | 31 Bytes           | Initial commit with minimal documentation.     | Uploaded          |
| `config.json`                                     | 31 Bytes           | Configuration settings for model initialization. | Uploaded          |

### **Key Features**

1. **Song Generation:**  
   - Generates full song lyrics based on user input, maintaining rhyme, meter, and thematic consistency.

2. **Music Context Understanding:**  
   - Trained on lyrics and song patterns to mimic and generate song-like content.

3. **Fine-tuned Creativity:**  
   - Fine-tuned using *Song-Catalogue-Long-Thought* for coherent lyric generation over extended prompts.

4. **Interactive Text Generation:**  
   - Designed for use cases like generating lyrical ideas, creating drafts for songwriters, or exploring themes musically.

---
### **Training Details**

- **Base Model:** [meta-llama/Llama-3.2-3B-Instruct](#)  
- **Finetuning Dataset:** [prithivMLmods/Song-Catalogue-Long-Thought](#)  
  - This dataset comprises 57.7k examples of lyrical patterns, song fragments, and themes.

---
### **Applications**

1. **Songwriting AI Tools:**  
   - Generate lyrics for genres like pop, rock, rap, classical, and others.

2. **Creative Writing Assistance:**  
   - Assist songwriters by suggesting lyric variations and song drafts.

3. **Storytelling via Music:**  
   - Create song narratives using custom themes and moods.

4. **Entertainment AI Integration:**  
   - Build virtual musicians or interactive lyric-based content generators.

---

### **Example Usage**

#### **Setup**
First, load the Llama-Song-Stream model:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Llama-Song-Stream-3B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
```

---

#### **Generate Lyrics Example**
```python
prompt = "Write a song about freedom and the open sky"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, temperature=0.7, num_return_sequences=1)

generated_lyrics = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_lyrics)
```

---

### **Deployment Notes**

1. **Serverless vs. Dedicated Endpoints:**  
   The model currently does not have enough usage for a serverless endpoint. Options include:
   - **Dedicated inference endpoints** for faster responses.
   - **Custom integrations via Hugging Face inference tools.**

2. **Resource Requirements:**  
   Ensure sufficient GPU memory and compute for large PyTorch model weights.

---