Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Wikillama.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+# WikiLlama
+
+![Accuracy](https://img.shields.io/badge/Accuracy-30%25-green)
+
+**WikiLlama** is a LoRA fine-tuned version of TinyLlama-1.1B, trained on the WikiText-103 dataset to improve general NLP performance.
+
+---
+
+## Model Details
+
+* **Base Model:** `TinyLlama/TinyLlama-1.1B-Chat-v1.0`
+* **Training Dataset:** WikiText-103
+* **Training Method:** LoRA (Low-Rank Adaptation) with base weights frozen.
+* **Author:** [Rudransh Joshi](https://rudransh.kafalfpc.com/)
+* **License:** Same as TinyLlama
+
+---
+
+## Evaluation & Performance
+
+The model was evaluated on the **HellaSwag** dataset (Sentence Completion / Multiple Choice) using a sample size of **100 examples**. The results demonstrate a significant accuracy improvement over the base model.
+
+| Model | Accuracy (HellaSwag) |
+| :--- | :--- |
+| Original TinyLlama | 24% |
+| WikiLlama (LoRA) | 30% |
+
+---
+## Example Usage 
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load the model and tokenizer
+model_id = "rudranshjoshi/WikiLlama"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# Prepare input
+messages = [
+    {"role": "user", "content": "What is the capital of France?"}
+]
+
+# Apply chat template (if available) or format prompt
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+# Generate response
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    temperature=0.7,
+    do_sample=True
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+
+ ``` 
+
+> **Note:** Fine-tuning on WikiText-103 resulted in a **6% absolute improvement** in accuracy on the HellaSwag benchmark compared to the vanilla TinyLlama-1.1B checkpoint.

Wikillama.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b96d1fb2d29da952d6bec41e9cdf0e891b849b5a7c646ce07a1dad5622b271
+size 4400929824

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274e251299a7c2edda21cd630e8147df303ce09cde92a621c3810651038fedf5
+size 2200119664

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}