commit 5a0746958d59cb09908d79631d9b34dae02a76cd Author: ModelHub XC Date: Sun May 31 11:32:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ramyaa1113/gemma2b-webxr-showroom-v2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..08073b7 --- /dev/null +++ b/README.md @@ -0,0 +1,292 @@ +--- +library_name: transformers +pipeline_tag: text-generation +base_model: google/gemma-2b +language: +- en +tags: +- text-generation +- conversational +- small-language-model +- webxr +- virtual-assistant +- xr-ai +- babylonjs +- immersive-ai +datasets: +- custom +license: gemma +--- + + +# gemma2b-webxr-showroom-v2 + +Fine-tuned Small Language Model designed for **AI-assisted interactions inside WebXR virtual showrooms and immersive product environments**. + +This model powers conversational assistants that guide users through **3D product experiences**, explain features, and answer questions in immersive environments. + +--- + +# Model Details + +## Model Description + +**gemma2b-webxr-showroom-v2** is a fine-tuned conversational model based on **Gemma 2B**. +It is optimized to act as an **AI showroom assistant** in immersive XR applications. + +The model was trained to generate responses related to: + +* product explanations +* feature descriptions +* interactive showroom guidance +* conversational product queries +* virtual retail assistance + +The model is part of the **IntelliShop XR project**, which demonstrates how **AI assistants can enhance WebXR product exploration experiences**. + +--- + +### Developed by + +Rajalakshmi Mahadevan (Ramya) + +### Model Type + +Causal Language Model (Text Generation) + +### Language + +English + +### License + +Gemma license (inherits base model licensing requirements) + +### Finetuned From + +google/gemma-2b + +--- + +# Model Sources + +Repository +https://huggingface.co/ramyaa1113/gemma2b-webxr-showroom-v2 + +Project Context +IntelliShop XR – AI Assisted Virtual Showroom + +--- + +# Intended Uses + +## Direct Use + +This model is designed to function as a **virtual assistant inside immersive environments**. + +Example uses include: + +* WebXR virtual product showrooms +* immersive e-commerce experiences +* AI guides inside 3D environments +* product demonstration assistants +* conversational retail bots + +Example interaction: + +User +Tell me about this XR headset. + +Assistant +This XR headset features a high-resolution display, inside-out tracking, and hand tracking support designed for immersive experiences. + +--- + +## Downstream Use + +The model can be integrated into larger systems such as: + +* WebXR applications +* Babylon.js interactive environments +* AI powered virtual stores +* conversational interfaces for immersive applications + +Typical architecture: + +WebXR Application +→ Backend API +→ gemma2b-webxr-showroom-v2 +→ AI response returned to user + +--- + +## Out-of-Scope Use + +This model is **not intended for**: + +* medical advice +* legal consultation +* financial decision making +* safety critical systems + +The model is optimized specifically for **interactive product assistance scenarios**. + +--- + +# Bias, Risks, and Limitations + +Like most language models, this model may: + +* produce incorrect or incomplete information +* generate hallucinated details +* reflect biases present in training data + +Additionally, the model is **domain tuned**, meaning performance may degrade for topics unrelated to product explanations or showroom interactions. + +--- + +# Recommendations + +To improve reliability: + +* use structured product metadata as context +* restrict prompts to product related queries +* implement response validation in production systems + +--- + +# How to Use the Model + +Example using Transformers: + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "ramyaa1113/gemma2b-webxr-showroom-v2" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id) + +prompt = "Explain the features of this XR headset." + +inputs = tokenizer(prompt, return_tensors="pt") + +outputs = model.generate( + **inputs, + max_new_tokens=150 +) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +--- + +# Training Details + +## Training Data + +A custom dataset of approximately **15,000 samples** was created for training. + +The dataset includes: + +* product explanation prompts +* conversational showroom interactions +* feature descriptions +* assistant style product responses +* retail dialogue examples + +The dataset was curated to simulate **real user interactions inside virtual showrooms**. + +--- + +## Training Procedure + +### Training Environment + +Initial experiments were conducted using **Google Colab**, but runtime instability and GPU limits caused interruptions. + +Training was then migrated to **Kaggle GPU notebooks**, which provided a more stable environment for completing the training pipeline. + +### Training Regime + +Mixed precision training (fp16) + +--- + +# Evaluation + +Formal benchmark evaluation has not yet been conducted. +Evaluation currently focuses on **qualitative testing within XR product interaction scenarios**. + +Testing scenarios include: + +* product explanation quality +* conversational response clarity +* interactive assistant behavior in virtual environments + +--- + +# Environmental Impact + +Estimated training environment: + +Hardware Type +NVIDIA T4 GPU + +Compute Platform +Kaggle Notebooks + +Training Duration +Several training runs across multiple sessions + +Carbon emissions are estimated to be relatively low due to the small model size and limited training duration. + +--- + +# Technical Specifications + +## Model Architecture + +Base architecture +Gemma 2B transformer decoder + +Task +Causal language modeling (text generation) + +--- + +## Compute Infrastructure + +### Hardware + +NVIDIA T4 GPU (Kaggle) + +### Software + +Python +PyTorch +Transformers +Hugging Face ecosystem + +--- + +# Author + +Rajalakshmi Mahadevan (Ramya) + +XR and AI Developer working at the intersection of: + +* Extended Reality (XR) +* WebXR +* Real-time 3D systems +* AI-powered immersive experiences + +--- + +# Model Card Contact + +For questions or collaboration: + +Hugging Face +https://huggingface.co/ramyaa1113 \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..923ec25 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4ae4928 --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "dtype": "float16", + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "transformers_version": "5.2.0", + "use_bidirectional_attention": null, + "use_cache": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4330053 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d32d98c --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb20b395e54825a2c920697416acf56769957753830da364caf816f1f92161b8 +size 5012363688 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..d934af0 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4adcd4b80a962290f1ad489ecf8f1d91009d736381c98d9ac54c949b6a7e42 +size 34349305 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..43d7982 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,19 @@ +{ + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": { + "start_of_turn": "", + "end_of_turn": "" + }, + "is_local": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} \ No newline at end of file