117 lines
4.9 KiB
Markdown
117 lines
4.9 KiB
Markdown
---
|
|
license: creativeml-openrail-m
|
|
datasets:
|
|
- prithivMLmods/Context-Based-Chat-Summary-Plus
|
|
language:
|
|
- en
|
|
base_model:
|
|
- meta-llama/Llama-3.2-3B-Instruct
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- safetensors
|
|
- chat-summary
|
|
- 3B
|
|
- Ollama
|
|
- text-generation-inference
|
|
- trl
|
|
- Llama3.2
|
|
---
|
|
|
|
### **Llama-Chat-Summary-3.2-3B: Context-Aware Summarization Model**
|
|
|
|
**Llama-Chat-Summary-3.2-3B** is a fine-tuned model designed for generating **context-aware summaries** of long conversational or text-based inputs. Built on the **meta-llama/Llama-3.2-3B-Instruct** foundation, this model is optimized to process structured and unstructured conversational data for summarization tasks.
|
|
|
|
|
|
| **File Name** | **Size** | **Description** | **Upload Status** |
|
|
|--------------------------------------------|------------------|--------------------------------------------------|-------------------|
|
|
| `.gitattributes` | 1.57 kB | Git LFS tracking configuration. | Uploaded |
|
|
| `README.md` | 42 Bytes | Initial commit with minimal documentation. | Uploaded |
|
|
| `config.json` | 1.03 kB | Model configuration settings. | Uploaded |
|
|
| `generation_config.json` | 248 Bytes | Generation-specific configurations. | Uploaded |
|
|
| `pytorch_model-00001-of-00002.bin` | 4.97 GB | Part 1 of the PyTorch model weights. | Uploaded (LFS) |
|
|
| `pytorch_model-00002-of-00002.bin` | 1.46 GB | Part 2 of the PyTorch model weights. | Uploaded (LFS) |
|
|
| `pytorch_model.bin.index.json` | 21.2 kB | Index file for the model weights. | Uploaded |
|
|
| `special_tokens_map.json` | 477 Bytes | Mapping of special tokens for the tokenizer. | Uploaded |
|
|
| `tokenizer.json` | 17.2 MB | Pre-trained tokenizer file. | Uploaded (LFS) |
|
|
| `tokenizer_config.json` | 57.4 kB | Configuration file for the tokenizer. | Uploaded |
|
|
|
|
### **Key Features**
|
|
|
|
1. **Conversation Summarization:**
|
|
- Generates concise and meaningful summaries of long chats, discussions, or threads.
|
|
|
|
2. **Context Preservation:**
|
|
- Maintains critical points, ensuring important details aren't omitted.
|
|
|
|
3. **Text Summarization:**
|
|
- Works beyond chats; supports summarizing articles, documents, or reports.
|
|
|
|
4. **Fine-Tuned Efficiency:**
|
|
- Trained with *Context-Based-Chat-Summary-Plus* dataset for accurate summarization of chat and conversational data.
|
|
|
|
---
|
|
### **Training Details**
|
|
|
|
- **Base Model:** [meta-llama/Llama-3.2-3B-Instruct](#)
|
|
- **Fine-Tuning Dataset:** [prithivMLmods/Context-Based-Chat-Summary-Plus](#)
|
|
- Contains **98.4k** structured and unstructured conversations, summaries, and contextual inputs for robust training.
|
|
|
|
---
|
|
### **Applications**
|
|
|
|
1. **Customer Support Logs:**
|
|
- Summarize chat logs or support tickets for insights and reporting.
|
|
|
|
2. **Meeting Notes:**
|
|
- Generate concise summaries of meeting transcripts.
|
|
|
|
3. **Document Summarization:**
|
|
- Create short summaries for lengthy reports or articles.
|
|
|
|
4. **Content Generation Pipelines:**
|
|
- Automate summarization for newsletters, blogs, or email digests.
|
|
|
|
5. **Context Extraction for AI Systems:**
|
|
- Preprocess chat or conversation logs for downstream AI applications.
|
|
|
|
#### **Load the Model**
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "prithivMLmods/Llama-Chat-Summary-3.2-3B"
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
model = AutoModelForCausalLM.from_pretrained(model_name)
|
|
```
|
|
#### **Generate a Summary**
|
|
```python
|
|
prompt = """
|
|
Summarize the following conversation:
|
|
User1: Hey, I need help with my order. It hasn't arrived yet.
|
|
User2: I'm sorry to hear that. Can you provide your order number?
|
|
User1: Sure, it's 12345.
|
|
User2: Let me check... It seems there was a delay. It should arrive tomorrow.
|
|
User1: Okay, thank you!
|
|
"""
|
|
|
|
inputs = tokenizer(prompt, return_tensors="pt")
|
|
outputs = model.generate(**inputs, max_length=100, temperature=0.7)
|
|
|
|
summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
|
print("Summary:", summary)
|
|
```
|
|
---
|
|
### **Expected Output**
|
|
**"The user reported a delayed order (12345), and support confirmed it will arrive tomorrow."**
|
|
|
|
---
|
|
### **Deployment Notes**
|
|
|
|
- **Serverless API:**
|
|
This model currently lacks sufficient usage for serverless endpoints. Use **dedicated endpoints** for deployment.
|
|
|
|
- **Performance Requirements:**
|
|
- GPU with sufficient memory (recommended for large models).
|
|
- Optimization techniques like quantization can improve efficiency for inference.
|
|
|
|
--- |