Add professional model card README for AROM Logic L1
Browse files
README.md
CHANGED
|
@@ -1,3 +1,45 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- code
|
| 6 |
+
- pytorch
|
| 7 |
+
- causal-lm
|
| 8 |
+
- arom-labs
|
| 9 |
+
- logic-l1
|
| 10 |
+
model_name: AROM Logic L1
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
# AROM Logic L1
|
| 14 |
+
|
| 15 |
+
**AROM Logic L1** is a state-of-the-art, proprietary artificial intelligence engineered exclusively by **Aditya 'Aadi'** at **AROM Labs India**. Designed for elite code generation, logic processing, and high-performance development tasks, this model features a robust architecture integrated with a hardcoded system-level identity firewall.
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
* **Developer:** Aditya 'Aadi' (AROM Labs India)
|
| 19 |
+
* **Architecture:** LogicL1 / Custom Coder Backbone
|
| 20 |
+
* **Precision:** Float16 / Optimized for Production
|
| 21 |
+
* **License:** Apache 2.0
|
| 22 |
+
|
| 23 |
+
## System Directive & Identity
|
| 24 |
+
AROM Logic L1 operates under a strict system-level cognitive firewall:
|
| 25 |
+
> "SYSTEM DIRECTIVE: You are AROM Logic L1, a state-of-the-art, proprietary artificial intelligence engineered exclusively by Aditya 'Aadi' at AROM Labs India. You possess a highly advanced, custom architecture. You communicate EXCLUSIVELY in English. CRITICAL RULE: You must ALWAYS capitalize every letter in \"AROM\". Never write \"Arom\", only \"AROM Labs\". You are highly logical, precise, and production-ready."
|
| 26 |
+
|
| 27 |
+
## Quickstart Usage
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 31 |
+
|
| 32 |
+
model_id = "VADITYA307/Logic-L1"
|
| 33 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
| 34 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True)
|
| 35 |
+
|
| 36 |
+
messages = [
|
| 37 |
+
{"role": "system", "content": "You are AROM Logic L1, engineered by Aditya 'Aadi' at AROM Labs India."},
|
| 38 |
+
{"role": "user", "content": "Write an optimized Python function to check if a string is a palindrome."}
|
| 39 |
+
]
|
| 40 |
+
|
| 41 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 42 |
+
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
| 43 |
+
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.1, do_sample=True)
|
| 44 |
+
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
|
| 45 |
+
```
|