|
|
--- |
|
|
library_name: transformers |
|
|
tags: [causal-lm, lora, fine-tuned, qwen, deepseek] |
|
|
--- |
|
|
|
|
|
# Model Card for Qwen-1.5B-LoRA-philosophy |
|
|
|
|
|
This model is a LoRA-fine-tuned causal language model based on `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`. It was trained on a custom philosophy dataset with fields `"prompt"` and `"completion"`. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
A parameter-efficient fine-tuning of a 1.5B-parameter Qwen-based model. |
|
|
At inference time, you can feed it a text prompt and it will generate the continuation. |
|
|
|
|
|
- **Developed by:** |
|
|
- **Funded by [optional]:** |
|
|
- **Shared by [optional]:** |
|
|
- **Model type:** Causal Language Model (LM) with LoRA adapters |
|
|
- **Language(s) (NLP):** English |
|
|
- **License:** |
|
|
- **Finetuned from model [optional]:** deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
|
|
|
|
|
### Model Sources [optional] |
|
|
|
|
|
- **Repository:** https://huggingface.co/your-username/small-fine-tunes |
|
|
- **Paper [optional]:** |
|
|
- **Demo [optional]:** |
|
|
|
|
|
## Uses |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
This model can be used out-of-the-box for text generation tasks such as chatbots, text completion, and conversational AI workflows. |
|
|
|
|
|
### Downstream Use [optional] |
|
|
|
|
|
Developers can further fine-tune or adapt the model for domain-specific conversation, question answering, or summarization tasks. |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
- High-stakes decision making without human oversight |
|
|
- Generation of disallowed or sensitive content |
|
|
- Real-time safety-critical systems |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
Since the base model and the fine-tuning data are proprietary or custom, unknown biases may exist. The model may: |
|
|
|
|
|
- Produce incorrect or hallucinatory statements |
|
|
- Reflect biases present in the source data |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
- Always review generated text for factual accuracy. |
|
|
- Do not rely on this model for safety-critical applications without additional guardrails. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("your-username/small-fine-tunes") |
|
|
model = AutoModelForCausalLM.from_pretrained("your-username/small-fine-tunes") |
|
|
|
|
|
generator = pipeline("text-generation", model=model, tokenizer=tokenizer) |
|
|
output = generator("Once upon a time", max_length=100) |
|
|
print(output[0]["generated_text"]) |
|
|
|
