70 lines
2.2 KiB
Markdown
70 lines
2.2 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
tags:
|
|
- text-generation-inference
|
|
- transformers
|
|
- smolify
|
|
- dslm
|
|
pipeline_tag: text-generation
|
|
inference:
|
|
parameters:
|
|
temperature: 1
|
|
top_p: 0.95
|
|
top_k: 64
|
|
---
|
|
|
|
# 🤏 smolified-protein-content
|
|
|
|
> **Intelligence, Distilled.**
|
|
|
|
This is a **Domain Specific Language Model (DSLM)** generated by the **Smolify Foundry**.
|
|
|
|
It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.
|
|
|
|
## 📦 Asset Details
|
|
- **Origin:** Smolify Foundry (Job ID: `835f8c65`)
|
|
- **Architecture:** gemma-3-270m
|
|
- **Training Method:** Proprietary Neural Distillation
|
|
- **Optimization:** 4-bit Quantized / FP16 Mixed
|
|
- **Dataset:** [Link to Dataset](https://huggingface.co/datasets/harshit1308/smolified-protein-content)
|
|
|
|
## 🚀 Usage (Inference)
|
|
This model is compatible with standard inference backends like vLLM, and Hugging Face Transformers.
|
|
|
|
```python
|
|
# Example: Running your Sovereign Model
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_id = "harshit1308/smolified-protein-content"
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
|
|
|
messages = [
|
|
{"role": "system", "content": '''You are a professional nutrition assistant. Provide the estimated protein content for food items based on the quantity specified by the user. Respond with the item name and the total protein amount in grams.'''},
|
|
{"role": "user", "content": '''Whey Protein Powder: 30g'''}
|
|
]
|
|
text = tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize = False,
|
|
add_generation_prompt = True,
|
|
)
|
|
if "gemma-3-270m" == "gemma-3-270m":
|
|
text = text.removeprefix('<bos>')
|
|
|
|
from transformers import TextStreamer
|
|
_ = model.generate(
|
|
**tokenizer(text, return_tensors = "pt").to(model.device),
|
|
max_new_tokens = 1000,
|
|
temperature = 1.0, top_p = 0.95, top_k = 64,
|
|
streamer = TextStreamer(tokenizer, skip_prompt = True),
|
|
)
|
|
```
|
|
|
|
## ⚖️ License & Ownership
|
|
This model weights are a sovereign asset owned by **harshit1308**.
|
|
Generated via [Smolify.ai](https://smolify.ai).
|
|
|
|
[<img src="https://smolify.ai/smolify.gif" width="100"/>](https://smolify.ai)
|