Upload folder using huggingface_hub

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1708940334

README.md

@@ -0,0 +1,106 @@
+---
+frameworks:
+- Pytorch
+license: apache-2.0
+tasks:
+- visual-question-answering
+- KarmaVLM
+---
+
+<h1 align="center">🧘🏻‍♂️ KarmaVLM (相生) </h1>
+<div align=center><img src ="./logo-github.png"/></div> 
+
+<p align="center">
+<a href="https://github.com/X-D-Lab/KarmaVLM"><img src="https://img.shields.io/badge/GitHub-24292e" alt="github"></a>
+<a href="https://huggingface.co/X-D-Lab"><img src="https://img.shields.io/badge/-HuggingFace-yellow" alt="HuggingFace"></a>
+<a href="https://modelscope.cn/organization/X-D-Lab"><img src="https://img.shields.io/badge/ModelScope-blueviolet" alt="modelscope"></a>
+<a href="https://openi.pcl.ac.cn/XD-LAB/KarmaVLM"><img src="https://img.shields.io/badge/-OpenI-337AFF" alt="OpenI"></a>
+<a href="https://WiseModel.cn/models/X-D%20Lab"><img src="https://img.shields.io/badge/WiseModel-561253" alt="WiseModel"></a>
+</p> 
+
+
+<div align="center">
+
+[![GitHub license](https://img.shields.io/github/license/X-D-Lab/KarmaVLM
+)](https://github.com/X-D-Lab/KarmaVLM/blob/main/LICENSE)
+[![GitHub Stars](https://img.shields.io/github/stars/X-D-Lab/KarmaVLM)](https://github.com/X-D-Lab/KarmaVLM/stargazers)
+[![GitHub Forks](https://img.shields.io/github/forks/X-D-Lab/KarmaVLM)](https://github.com/X-D-Lab/KarmaVLM/fork)
+[![GitHub Contributors](https://img.shields.io/github/contributors/X-D-Lab/KarmaVLM)](https://github.com/X-D-Lab/KarmaVLM/graphs/contributors)  
+
+</div>
+
+
+# 👏 Introduction
+KarmaVLM is a family of high efficiency and powerful visual language model (VLM) pretrained with interleaved image-text data at scale, enabling content comprehension, recognition, and multi-round conversations about images.
+
+# 🎉 News
+* [2024/02] KarmaVLM is released. 
+
+# ⚡️Features
+KarmaVLM offers the following features:
+
+- **High Efficiency**: KarmaVLM focuses on exploring the capabilities of small parametric quantitative models on multimodal tasks. So, KarmaVLM can be efficiently deployed on most GPU cards and personal computers, and even on end devices such as mobile phones.
+
+- **Multi-round text-image conversations**: KarmaVLM can take both text and images as inputs and produce text outputs. Currently, it supports multi-round visual question answering with one image.
+
+- **Strong image comprehension**: KarmaVLM is adept at analyzing visuals, making it an efficient tool for tasks like extracting, organizing, and summarizing information from images. 
+
+# 🔥Model Zoo
+| Checkpoint | Download | Vision Encoder | LLM | MMBench | 
+| :----: | :----: | :----: | :----: | :----: |
+| KarmaVLM-Qwen1.5-0_5B | 🤗 / 🤖 | openai/clip-vit-large-patch14-336 | Qwen/Qwen1.5-0.5B | 53.5 |
+
+Other Benchmark evaluations are in progress!
+
+# 👨‍💻 Quick Start
+
+## Requirements and Installation
+
+```
+git clone https://github.com/X-D-Lab/KarmaVLM.git
+cd KarmaVLM
+
+conda create -n karmavlm python=3.10 -y
+conda activate karmavlm
+
+pip install --upgrade pip  # enable PEP 660 support
+pip install -e .
+pip install -e ".[train]"
+pip install flash-attn --no-build-isolation
+```
+
+## 🌏 Demo
+1. CLI Inference
+    ```
+    python -m llava.serve.cli \
+        --model-path /path/to/karmavlm/model \
+        --model-type qwen \
+        --image-file /path/to/the/test/image
+    ```
+2. Gradio Web UI
+
+  - Starting the Controller
+    ```
+    python -m llava.serve.gradio_web_server \
+	--controller http://localhost:10000 \
+	--model-list-mode reload
+    --share ##(optional)
+    ```
+  - Launching the Gradio Web Server
+    ```
+    python -m llava.serve.model_worker \
+    --host 0.0.0.0 \
+    --controller http://localhost:10000 \
+    --port 40000 \
+    --worker http://localhost:40000 \
+    --model-path /path/to/karmavlm/model \
+    --model-type qwen
+    ```
+
+# 📋 License
+This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses. The content of this project itself is licensed under the [Apache license 2.0](./LICENSE).
+
+# 🙇‍ Architecture
+We build our project based on [LLaVA](https://github.com/haotian-liu/LLaVA): Large Language and Vision Assistant.
+
+

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|extra_0|>": 151646,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,42 @@
+{
+    "_name_or_path": "./X-D-Lab/qwen/Qwen1.5-0_5B",
+    "architectures": [
+      "LlavaQwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "freeze_mm_mlp_adapter": false,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_aspect_ratio": "pad",
+    "image_projector_type": "mlp2x_gelu",
+    "initializer_range": 0.02,
+    "intermediate_size": 2816,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 21,
+    "mm_hidden_size": 1024,
+    "mm_vision_tower": "openai/clip-vit-large-patch14",
+    "mm_projector_lr": null,
+    "mm_use_im_patch_token": false,
+    "mm_use_im_start_end": false,
+    "mm_vision_select_feature": "patch",
+    "mm_vision_select_layer": -2,
+    "model_type": "llava_qwen2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "pad_token_id": 151646,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": true,
+    "tokenizer_padding_side": "right",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.2",
+    "tune_mm_mlp_adapter": false,
+    "use_cache": true,
+    "use_mm_proj": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e293f2297e18d64f29a8b64802a1632969a1f3cfa82a348a4ba5c554b0d0960c
+size 1849792256

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|extra_0|>",
+  "unk_token": {
+    "content": "<|extra_0|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|extra_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|extra_0|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|extra_0|>"
+}