Upload folder using huggingface_hub

README.md

@@ -1,125 +1,79 @@
 ---
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-library_name: peft
-pipeline_tag: text-generation
 license: mit
 language:
-- en
+  - en
+library_name: transformers
 tags:
-- tinyllama
-- shakespeare
-- lora
-- peft
-- fine-tuned
-- text-generation
-- causal-lm
+  - shakespeare
+  - chatbot
+  - tinyllama
+  - fine-tuned
+  - conversational
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+pipeline_tag: text-generation
 ---
 
-# TinyLlama Shakespeare 🎭
-
-A fine-tuned version of [TinyLlama-1.1B-Chat](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) trained on Shakespeare's complete works to generate Shakespearean-style text.
+# TinyLlama Shakespeare Chatbot
 
-## Model Details
+A conversational AI that speaks in authentic Shakespearean English.
 
-- **Base Model:** TinyLlama/TinyLlama-1.1B-Chat-v1.0
-- **Fine-tuning Method:** LoRA (Low-Rank Adaptation)
-- **Quantization:** 4-bit (NF4) via bitsandbytes
-- **Developed by:** [Akash Nath](https://github.com/Akash-nath29)
-- **License:** MIT
-- **Language:** English
+## Model Description
 
-## Training Details
-
-### Training Data
-The model was fine-tuned on Shakespeare's complete works including sonnets, plays, and poems (~42,000 lines of text).
+Fine-tuned on Shakespeare's complete works (42,000+ lines) transformed into 8,000+ chat-style training examples.
 
-### Training Configuration
+**Capabilities:**
+- Compose sonnets on any topic
+- Engage in dramatic dialogue
+- Respond in Shakespearean style
+- Generate poetry and monologues
 
-| Parameter | Value |
-|-----------|-------|
-| LoRA Rank (r) | 16 |
-| LoRA Alpha | 32 |
-| Target Modules | q_proj, v_proj |
-| LoRA Dropout | 0.05 |
-| Batch Size | 2 |
-| Gradient Accumulation | 4 |
-| Learning Rate | 2e-4 |
-| Epochs | 2 |
-| Precision | FP16 |
-| Max Sequence Length | 256 |
-
-### Hardware
-- **GPU:** NVIDIA GeForce RTX 3050 Laptop GPU
-- **Training Time:** ~4 hours
+**This is a MERGED model** - works directly with transformers, no PEFT needed!
 
 ## Usage
 
-### Quick Start
-
-```python
-from peft import PeftModel
+`python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-# Load base model and tokenizer
-base_model = AutoModelForCausalLM.from_pretrained(
-    "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-    load_in_4bit=True,
+model = AutoModelForCausalLM.from_pretrained(
+    "Akash-nath29/tinyllamashakespeare",
+    torch_dtype=torch.float16,
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
-
-# Load LoRA adapters
-model = PeftModel.from_pretrained(base_model, "Akash-nath29/tinyllamashakespeare")
+tokenizer = AutoTokenizer.from_pretrained("Akash-nath29/tinyllamashakespeare")
 
 # Generate text
-prompt = "To be or not to be"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_length=200, do_sample=True, temperature=0.7)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
-
-### Using the Training Repository
+inputs = tokenizer("To be or not to be", return_tensors="pt")
+outputs = model.generate(**inputs, max_length=200)
+print(tokenizer.decode(outputs[0]))
+`
 
-```bash
-git clone https://github.com/Akash-nath29/TinyLlamaShakespeare
-cd TinyLlamaShakespeare
-pip install -r requirements.txt
-
-# Run inference
-python scripts/inference.py --model_path Akash-nath29/tinyllamashakespeare --prompt "Shall I compare thee"
-```
+## Training Details
 
-## Example Outputs
+| Parameter | Value |
+|-----------|-------|
+| Base Model | TinyLlama-1.1B-Chat-v1.0 |
+| Method | LoRA + QLoRA (4-bit) |
+| LoRA Rank | 16 |
+| LoRA Alpha | 32 |
+| Target Modules | q_proj, k_proj, v_proj, o_proj |
+| Training Examples | 8,000+ conversations |
+| Max Length | 512 tokens |
+| Epochs | 3 |
 
-**Prompt:** "To be or not to be"
+## Hardware
 
-**Output:** "To be or not to be, that's the question. I have seen you with the duke, and I know he is a man..."
+- GPU: NVIDIA GeForce RTX 3050 Laptop GPU
+- Training Time: ~4 hours
 
-## Limitations
+## Developed By
 
-- The model is trained primarily on Shakespearean text and may not perform well on modern language tasks
-- Output quality varies based on prompts and generation parameters
-- The model inherits biases present in the base TinyLlama model and Shakespeare's original texts
+[Akash Nath](https://github.com/Akash-nath29)
 
 ## Repository
 
-- **GitHub:** [https://github.com/Akash-nath29/TinyLlamaShakespeare](https://github.com/Akash-nath29/TinyLlamaShakespeare)
-
-## Citation
-
-```bibtex
-@misc{tinyllamashakespeare,
-  author = {Akash Nath},
-  title = {TinyLlama Shakespeare: Fine-tuned TinyLlama on Shakespeare's Works},
-  year = {2025},
-  publisher = {HuggingFace},
-  url = {https://huggingface.co/Akash-nath29/tinyllamashakespeare}
-}
-```
+[GitHub - TinyLlamaShakespeare](https://github.com/Akash-nath29/TinyLlamaShakespeare)
 
-## Framework Versions
+## License
 
-- PEFT 0.18.0
-- Transformers 4.x
-- PyTorch 2.6.0+cu124
-- bitsandbytes 0.41+
+MIT License

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3376f88996d7b07eda95785f406e7180085c64396d8312ed9f2a7f81bb842d01
+oid sha256:b5a2901f9122c729b2f34c9fbef1cdb01c93312b167080827e1b08d97107ffa7
 size 2200119664

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -33,11 +33,15 @@
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "legacy": false,
+  "max_length": 512,
   "model_max_length": 2048,
   "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }