Upload 13 files

Initial commit. Git is broken. Checking out after intial upload

README.md

@@ -1,3 +1,71 @@
 ---
-license: cc-by-4.0
+license: cc-by-sa-4.0
+language:
+- en
+tags:
+- Multimodal
+- StableLM
+datasets:
+- LDJnr/Capybara
+- LDJnr/LessWrong-Amplify-Instruct
+- LDJnr/Pure-Dove
+- LDJnr/Verified-Camel
 ---
+
+# Obsidian: Worlds smallest multi-modal LLM. First multi-modal model in size 3B
+
+## Model Name: Obsidian-3B-V0.5
+
+Obsidian is a brand new series of Multimodal Language Models. This first project is led by Quan N. and Luigi D.(LDJ).
+
+Obsidian-3B-V0.5 is a multi-modal AI model that has vision! it's smarts are built on [Capybara-3B-V1.9](https://huggingface.co/NousResearch/Capybara-3B-V1.9) based on [StableLM-3B-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t). Capybara-3B-V1.9 achieves state-of-the-art performance when compared to model with similar size, even beats some 7B models.
+
+Current finetuning and inference code is available on our GitHub repo: [Here](https://github.com/NousResearch/Obsidian)
+
+## Acknowledgement
+
+Obsidian-3B-V0.5 was developed and finetuned by [Nous Research](https://huggingface.co/NousResearch), in collaboration with [Virtual Interactive](https://huggingface.co/vilm).
+Special thank you to **LDJ** for the wonderful Capybara dataset, and **qnguyen3** for the model training procedure.
+## Model Training
+
+Obsidian-3B-V0.5 followed the same training procedure as LLaVA 1.5
+
+## Prompt Format
+
+The model followed ChatML format. However, with `###` as the seperator
+
+```
+<|im_start|>user
+What is this sign about?\n<image>
+###
+<|im_start|>assistant
+The sign is about bullying, and it is placed on a black background with a red background.
+###
+```
+
+## Benchmarks
+
+Coming Soon!
+
+
+Citation:
+
+```
+@article{nguyen2023Obsidian-3B,
+  title={Obsidian-3B: First Multi-modal below 7B Parameters.},
+  author={Nguyen, Quan and Daniele},
+  journal={HuggingFace:https://huggingface.co/NousResearch/Obsidian-3B-V0.5},
+  year={2023}
+}
+```
+
+Acknowledgements:
+
+```
+@article{daniele2023amplify-instruct,
+  title={Amplify-Instruct: Synthetically Generated Diverse Multi-turn Conversations for Effecient LLM Training.},
+  author={Daniele, Luigi and Suphavadeeprasit},
+  journal={arXiv preprint arXiv:(comming soon)},
+  year={2023}
+}
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "NousResearch/Obsidian-3B-V0.5",
+  "architectures": [
+    "LlavaStableLMEpochForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_stablelm_epoch",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rope_pct": 0.25,
+  "rope_theta": 10000,
+  "rotary_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.34.1"
+}

handler.py

@@ -0,0 +1,40 @@
+from typing import Dict, List, Any
+from transformers import pipeline
+from obsidian import Vision
+
+class EndpointHandler():
+    def __init__(self, path="", vision_model="obsidian3b"):
+        self.pipeline = pipeline("text-classification", model=path)
+        self.vision = Vision(vision_model)
+
+    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """
+        data args:
+            inputs (:obj: `str`)
+            image (:obj: `Image`)
+        Return:
+            A :obj:`list` | `dict`: will be serialized and returned
+        """
+        # get inputs
+        inputs = data.pop("inputs", "")
+        image = data.pop("image", None)
+
+        if image:
+            # perform image classification using Obsidian 3b vision
+            image_features = self.vision.encode_image(image)
+            image_embedding = self.vision.extract_feature(image_features)
+            image_caption = self.vision.generate_caption(image_embedding)
+
+            # combine text and image captions
+            combined_captions = [inputs, image_caption]
+
+            # run text classification on combined captions
+            prediction = self.pipeline(combined_captions, temperature=0.33, num_beams=5, stop=[])
+
+            return prediction
+
+        else:
+            # run text classification on plain text input
+            prediction = self.pipeline(inputs, temperature=0.33, num_beams=5, stop=[])
+
+            return prediction

mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67836e202ca22f809c2a8b5117cc774e1119770e35ce37a6ed53d05e22ae0de6
+size 18362424

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2a1f8f626c586ee15139590c7b63768ed3b3c756b12892be8466a2d050b3ca
+size 6216525942

requirements.txt

@@ -0,0 +1 @@
+obsidian

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,237 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ceb1055fa28417dfe2aea3217be11add461c4ce297769ce39eb6127af791d1
+size 7224