Update README.md

README.md

@@ -9,6 +9,11 @@ tags:
 - chat
 - conversational
 pipeline_tag: text-generation
+datasets:
+- LucidexAi/VIBE-2K
+- HuggingFaceTB/instruct-data-basics-smollm-H4
+- MuskumPillerum/General-Knowledge
+library_name: transformers
 ---
 
 # FuadeAI-50M
@@ -19,7 +24,7 @@ A 50 million parameter causal language model trained for conversational chat, bu
 
 | Property | Value |
 |---|---|
-| Parameters | ~50M |
+| Parameters | 51M |
 | Architecture | GPT-2 (custom config) |
 | Hidden size | 512 |
 | Layers | 8 |
@@ -39,33 +44,28 @@ A 50 million parameter causal language model trained for conversational chat, bu
 
 ## Training Data
 
-- [LucidexAi/VIBE-2K](https://huggingface.co/datasets/LucidexAi/VIBE-2K) — conversational prompts and responses
-- [HuggingFaceTB/instruct-data-basics-smollm-H4](https://huggingface.co/datasets/HuggingFaceTB/instruct-data-basics-smollm-H4) — instruction following
-- [MuskumPillerum/General-Knowledge](https://huggingface.co/datasets/MuskumPillerum/General-Knowledge) — general knowledge QA
+- [LucidexAi/VIBE-2K](https://huggingface.co/datasets/LucidexAi/VIBE-2K)
+- [HuggingFaceTB/instruct-data-basics-smollm-H4](https://huggingface.co/datasets/HuggingFaceTB/instruct-data-basics-smollm-H4)
+- [MuskumPillerum/General-Knowledge](https://huggingface.co/datasets/MuskumPillerum/General-Knowledge)
 - Custom synthetic dataset for identity and conversational grounding
 
 ## How To Use
 
-### Installation
-```bash
-pip install transformers torch
-```
-
-### Basic Inference
+### Transformers
 ```python
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
 import torch
 
 # Load model and tokenizer
-tokenizer = GPT2Tokenizer.from_pretrained("your-username/FuadeAI-50M")
-model = GPT2LMHeadModel.from_pretrained("your-username/FuadeAI-50M")
+tokenizer = GPT2Tokenizer.from_pretrained("Fu01978/FuadeAI-50M")
+model = GPT2LMHeadModel.from_pretrained("Fu01978/FuadeAI-50M")
 model.eval()
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = model.to(device)
 
 # Chat function
-def chat(prompt, temperature=0.7, top_p=0.9, max_new_tokens=100):
+def chat(prompt, temperature=0.4, top_p=0.9, max_new_tokens=100):
     formatted = (
         f"{tokenizer.bos_token}"
         f"<user>{prompt}</user>"
@@ -80,7 +80,7 @@ def chat(prompt, temperature=0.7, top_p=0.9, max_new_tokens=100):
             do_sample=True,
             temperature=temperature,
             top_p=top_p,
-            repetition_penalty=1.3,
+            repetition_penalty=1.2,
             no_repeat_ngram_size=3,
             eos_token_id=tokenizer.eos_token_id,
             pad_token_id=tokenizer.pad_token_id,
@@ -91,31 +91,27 @@ def chat(prompt, temperature=0.7, top_p=0.9, max_new_tokens=100):
 
 # Example usage
 print(chat("Hello!"))
-print(chat("What is photosynthesis?"))
+print(chat("Who invented the first telephone?"))
 print(chat("Who are you?"))
 ```
 
 ### Generation Tips
 
-- `temperature=0.7` — balanced creativity and coherence (recommended)
-- `temperature=0.3` — more focused and deterministic answers
-- `temperature=1.0` — more creative but less reliable
-- `repetition_penalty=1.3` — keeps responses from looping (recommended, do not remove)
-- `max_new_tokens=200` — increase for longer responses
+- `temperature=0.45` — balanced creativity and coherence (recommended)
+- `temperature=0.2` — more focused and deterministic answers
+- `temperature=0.8` — more creative but less reliable
+- `repetition_penalty=1.2` — keeps responses from looping (recommended)
+- `max_new_tokens=100` — increase for longer responses
 
 ## Limitations
 
 - **50M parameters is small** — factual recall is imperfect and some answers may be incorrect. Always verify factual claims from this model.
-- **Trained on ~10k samples** — coverage of topics is limited compared to large-scale models.
-- **Not suitable for** — factual research, medical/legal/financial advice, or any high-stakes decision making.
+- **Coverage of topics** is limited compared to large-scale models.
+- **Not suitable for** factual research, medical/legal/financial advice, or any high-stakes decision making.
 - **Context window** — limited to 1024 tokens total (prompt + response).
 
 ## Intended Use
 
 - Learning and experimentation with small language models
 - Lightweight conversational agent for low-stakes applications
-- Fine-tuning base for domain-specific chat applications
-
-## License
-
-MIT — free to use, modify, and distribute with attribution.
+- Fine-tuning base for domain-specific chat applications