Upload LLaVA-OneVision LoRA fine-tuned model on GuruShots dataset

README.md

@@ -1,3 +1,106 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+base_model: lmms-lab/llava-onevision-qwen2-0.5b-ov
+tags:
+- vision-language
+- multimodal
+- llava
+- lora
+- fine-tuned
+- gurushots
+- photography
+license: apache-2.0
+datasets:
+- Dataseeds/GuruShots-Sample-Dataset-GSD
+language:
+- en
+pipeline_tag: image-text-to-text
+---
+
+# LLaVA-OneVision-Qwen2-0.5b-ov Fine-tuned on GuruShots Dataset
+
+This model is a LoRA (Low-Rank Adaptation) fine-tuned version of [lmms-lab/llava-onevision-qwen2-0.5b-ov](https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov) on the GuruShots photography dataset.
+
+## Model Description
+
+- **Base Model**: LLaVA-OneVision-Qwen2-0.5b-ov
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **LoRA Rank**: 32
+- **LoRA Alpha**: 32
+- **LoRA Dropout**: 0.1
+- **Target Modules**: v_proj, k_proj, q_proj, up_proj, gate_proj, down_proj, o_proj
+- **Dataset**: GuruShots Sample Dataset (GSD) [Dataseeds/GuruShots-Sample-Dataset-GSD](https://huggingface.co/datasets/Dataseeds/GuruShots-Sample-Dataset-GSD)
+- **Task**: Vision-Language Understanding for Photography
+
+## Training Details
+
+This model was fine-tuned using LoRA on a curated dataset from GuruShots, focusing on photography-related vision-language tasks. The training was performed with:
+
+- LoRA rank: 32
+- LoRA alpha: 32
+- Dropout: 0.1
+- Target modules: All attention and MLP projection layers
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    "lmms-lab/llava-onevision-qwen2-0.5b-ov",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(
+    base_model,
+    "Dataseeds/LLaVA-OneVision-Qwen2-0.5b-ov-GSD-FineTune"
+)
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("lmms-lab/llava-onevision-qwen2-0.5b-ov")
+
+# Use the model for inference
+# (Add your inference code here)
+```
+
+## Model Architecture
+
+The model maintains the same architecture as the base LLaVA-OneVision model:
+- Vision Encoder: SigLIP-SO400M
+- Language Model: Qwen2-0.5B
+- Multimodal Projector: MLP with GELU activation
+
+## Training Data
+
+The model was fine-tuned on the GuruShots Sample Dataset, which contains photography images with associated metadata and descriptions.
+
+## Limitations and Biases
+
+This model inherits the limitations of the base LLaVA-OneVision model and may have additional biases introduced through the fine-tuning dataset. The model is specifically optimized for photography-related tasks and may not perform as well on general vision-language tasks.
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{llava-onevision-gsd-finetune,
+  title={LLaVA-OneVision Fine-tuned on GuruShots Dataset},
+  author={Dataseeds},
+  year={2024},
+  publisher={Hugging Face},
+  url={https://huggingface.co/Dataseeds/LLaVA-OneVision-Qwen2-0.5b-ov-GSD-FineTune}
+}
+
+@article{li2024llavaonevision,
+      title={LLaVA-OneVision}, 
+}
+```
+
+## License
+
+This model is released under the Apache 2.0 license, following the base model's licensing.

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmms-lab/llava-onevision-qwen2-0.5b-ov",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc055a3dbfc3e782b959393f04304c1cd15b95a422d6ff1512c06eae70976094
+size 81960088

added_tokens.json

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

config.json

@@ -0,0 +1,220 @@
+{
+  "_name_or_path": "lmms-lab/llava-onevision-qwen2-0.5b-ov",
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "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": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": null,
+  "model_type": "llava",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pos_skipping_range": 4096,
+  "projector_hidden_act": "gelu",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "model_type": "llama"
+  },
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vision_tower_pretrained": null
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.0.dev0"
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc7ec0fa71c49298d2e3eb49bd89edc0abfe2a4c9e636591ed48ed6dc1759fc
+size 991842600

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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": "<image>",
+      "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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}