Update README.md

README.md

@@ -1,3 +1,145 @@
 ---
 license: apache-2.0
+datasets:
+- HuggingFaceFW/fineweb-edu
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- supra
+- chimera
+- 50m
+- llama
+- small
+- open
+- open-source
+- cpu
+- tiny
+- slm
 ---
+
+# 🦅 Supra-50M Instruct
+
+**Supra-50M Instruct** is a compact 50M-parameter chat/instruct causal language model built by SupraLabs, trained from scratch using a Llama-style architecture on 20 billion tokens of high-quality educational web text. Despite being significantly smaller than comparable open models, it achieves competitive or superior results on several key benchmarks. It's our first SupraLabs Scaling Up Plan model.
+
+---
+
+## 📚 Training Data
+
+For the SFT (supervised finetuning) we used the full Alpaca-Cleaned dataset for 4 epochs. See the full SFT-code in sft.py
+
+---
+
+## ⚙️ Pretraining details
+For more details, the full code, configs and weights, please refer to [https://huggingface.co/SupraLabs/Supra-50M-Base](https://huggingface.co/SupraLabs/Supra-50M-Base)
+
+---
+
+## 🚀 Inference
+
+```python
+import torch
+from transformers import pipeline, AutoTokenizer
+
+# ── Config ────────────────────────────────────────────────────────────────────
+
+MODEL_ID = "SupraLabs/Supra-50M-Instruct/"  
+MAX_NEW_TOKENS = 512
+
+# ── Load pipeline directly from HF ────────────────────────────────────────────
+
+print(f"[*] Loading SFT model and tokenizer from HF Hub ({MODEL_ID})...")
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+pipe = pipeline(
+    "text-generation",
+    model=MODEL_ID,
+    tokenizer=tokenizer,
+    device_map="auto",
+    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32
+)
+
+print(f"[+] Pipeline ready — Model loaded using {pipe.model.device}")
+
+# ── Prompt template (must match sft.py exactly) ───────────────────────────────
+
+def build_prompt(instruction: str, input_text: str = "") -> str:
+    if input_text.strip():
+        return (
+            "Below is an instruction that describes a task, paired with an input "
+            "that provides further context. Write a response that appropriately "
+            "completes the request.\n\n"
+            f"### Instruction:\n{instruction}\n\n"
+            f"### Input:\n{input_text}\n\n"
+            "### Response:\n"
+        )
+    return (
+        "Below is an instruction that describes a task. Write a response that "
+        "appropriately completes the request.\n\n"
+        f"### Instruction:\n{instruction}\n\n"
+        "### Response:\n"
+    )
+
+# ── Generate ──────────────────────────────────────────────────────────────────
+
+def generate(instruction: str, input_text: str = "", max_new_tokens: int = MAX_NEW_TOKENS) -> str:
+    prompt = build_prompt(instruction, input_text)
+
+    result = pipe(
+        prompt,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.9,
+        repetition_penalty=1.15,
+        pad_token_id=pipe.tokenizer.pad_token_id,
+        eos_token_id=pipe.tokenizer.eos_token_id,
+        return_full_text=False
+    )
+    
+    return result[0]['generated_text'].strip()
+
+# ── Interactive loop ──────────────────────────────────────────────────────────
+
+if __name__ == "__main__":
+    print("\n[+] Ready. Type 'quit' to exit.\n")
+
+    while True:
+        instruction = input("Instruction: ").strip()
+        if instruction.lower() == "quit":
+            break
+
+        inp = input("Input (optional, Enter to skip): ").strip()
+
+        print("-" * 50)
+        print(generate(instruction, inp))
+        print()
+```
+
+---
+
+## 💬 Sample Outputs
+
+**User:** What is AI?<br>
+**Supra-50M Instruct:**:<br>
+AI refers to the simulation of human intelligence and creativity in machines, which are designed to mimic or surpass human cognition and reasoning. It is the process by which AI systems can solve problems, make predictions, or automate processes that typically require human-level thinking and problem solving. AI technology has been rapidly growing and evolving over time, with many potential benefits for society as a whole. Some of these include:
+1. Improved Accuracy: AI algorithms have demonstrated great accuracy in predicting outcomes, making accurate predictions on new data sets, and even answering real-world questions. This improves our ability to learn from experience and adapt to changing situations.
+2. Personalization: AI is used to personalize user experiences, such as recommending products based on their previous interactions and preferences. This helps people to stay motivated and maintain high levels of satisfaction.
+3. Better Decision Making: AI enables systems to analyze large amounts of data quickly and accurately, allowing us to make informed decisions more easily and
+
+<br>
+
+See samples.txt for more!
+
+---
+
+## 📄 License
+
+This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
+
+---
+
+*© SupraLabs 2026 — Project Chimera*