Upload fine-tuned TinyLlama e-commerce chatbot with LoRA adapter

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- fine-tuned
+- e-commerce
+- chatbot
+- lora
+- peft
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# TinyLlama-ECommerce-Chatbot
+
+This is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) for e-commerce customer service chatbot applications.
+
+## Model Details
+
+- **Base Model**: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Task**: E-commerce customer service conversation
+- **Training Data**: ChatML formatted e-commerce conversations
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model and tokenizer
+base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+tokenizer = AutoTokenizer.from_pretrained("ShenghaoYummy/TinyLlama-ECommerce-Chatbot")
+
+# Load the fine-tuned model
+model = PeftModel.from_pretrained(base_model, "ShenghaoYummy/TinyLlama-ECommerce-Chatbot")
+
+# Generate response
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.8)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Example usage
+prompt = "<|system|>\nYou are a helpful e-commerce assistant.<|im_end|>\n<|user|>\nWhat's your return policy?<|im_end|>\n<|assistant|>\n"
+response = generate_response(prompt)
+print(response)
+```
+
+## Training Details
+
+This model was fine-tuned using:
+- LoRA with rank 16
+- Learning rate optimization via Optuna
+- MLflow experiment tracking
+- DVC pipeline management
+
+## Limitations
+
+- Optimized for e-commerce customer service scenarios
+- May not perform well on general conversation topics
+- Responses are based on training data patterns
+
+## Citation
+
+If you use this model, please cite: @misc{ecommerce-chatbot-tinyllama,
+title={Fine-tuned TinyLlama for E-commerce Customer Service},
+author={Your Name},
+year={2024},
+url={https://huggingface.co/ShenghaoYummy/TinyLlama-ECommerce-Chatbot}
+}

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ccc0cf0c164e64922658d934fd369c85cfdd49ad1db6a89170f4a0b967f80d
+size 50503544

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_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}