Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,235 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+base_model:
+- lmms-lab/LLaVA-OneVision-1.5-8B-Instruct
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [lmms-lab/LLaVA-OneVision-1.5-8B-Instruct](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct).
+
+### Example usage:
+
+```python
+from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM
+from qwen_vl_utils import process_vision_info
+import torch
+
+# fix flash_attn_varlen_func, see https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5/pull/33/files
+from flash_attn.flash_attn_interface import flash_attn_varlen_func
+import transformers
+transformers.modeling_flash_attention_utils.flash_attn_varlen_func = flash_attn_varlen_func
+
+model_id = "tiny-random/llava-onevision-1.5"
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="cuda", trust_remote_code=True
+)
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=32)
+generated_ids_trimmed = [
+    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+### Codes to create this repo:
+
+```python
+import json
+from pathlib import Path
+
+import accelerate
+import torch
+from huggingface_hub import file_exists, hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoProcessor,
+    GenerationConfig,
+    AutoModelForImageTextToText,
+    set_seed,
+)
+# fix flash_attn_varlen_func, see https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5/pull/33/files
+from flash_attn.flash_attn_interface import flash_attn_varlen_func
+import transformers
+transformers.modeling_flash_attention_utils.flash_attn_varlen_func = flash_attn_varlen_func
+
+source_model_id = "lmms-lab/LLaVA-OneVision-1.5-8B-Instruct"
+save_folder = "/tmp/tiny-random/llava-onevision-1.5"
+
+processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+for k, v in config_json['auto_map'].items():
+    config_json['auto_map'][k] = f'{source_model_id}--{v}'
+
+config_json['text_config'].update({
+    'head_dim': 32,
+    'hidden_size': 8,
+    'intermediate_size': 64,
+    'num_hidden_layers': 2,
+    'num_attention_heads': 8,
+    'num_key_value_heads': 4,
+    'layer_types': ['full_attention'] * 2,
+    'max_window_layers': 2,
+})
+config_json['vision_config'].update(
+    {
+        'depth': 2,
+        'intermediate_size': 256,
+        'embed_dim': 32 * 4,
+        'hidden_size': 32 * 4,
+        'text_hidden_size': 8,
+        'num_heads': 4,
+        'num_hidden_layers': 2,
+    }
+)
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = AutoConfig.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+torch.set_default_dtype(torch.bfloat16)
+model = AutoModelForCausalLM.from_config(config, trust_remote_code=True).to(torch.bfloat16)
+torch.set_default_dtype(torch.float32)
+if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
+    model.generation_config = GenerationConfig.from_pretrained(
+        source_model_id, trust_remote_code=True,
+    )
+    model.generation_config.do_sample = True
+    print(model.generation_config)
+model = model.cpu()
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.1)
+        print(name, p.shape)
+model.save_pretrained(save_folder)
+
+def modify_automap(path, source_model_id):
+    import json
+    with open(path, 'r', encoding='utf-8') as f:
+        content = json.load(f)
+    automap = {}
+    if content.get('auto_map', None) is not None:
+        for key, value in content.get('auto_map').items():
+            if isinstance(value, str):
+                value = source_model_id + '--' + value.split('--')[-1]
+            else:
+                value = [(source_model_id + '--' + v.split('--')[-1]) if '.' in str(v) else v for v in value]
+            automap[key] = value
+        with open(path, 'w', encoding='utf-8') as f:
+            json.dump({**content, 'auto_map': automap}, f, indent=2)
+
+modify_automap(f"{save_folder}/config.json", source_model_id)
+# modify_automap(f'{save_folder}/processor_config.json', source_model_id)
+# modify_automap(f'{save_folder}/preprocessor_config.json', source_model_id)
+# modify_automap(f'{save_folder}/tokenizer_config.json', source_model_id)
+for python_file in Path(save_folder).glob('*.py'):
+    python_file.unlink()
+```
+
+### Printing the model:
+
+```text
+LLaVAOneVision1_5_ForConditionalGeneration(
+  (model): LLaVAOneVision1_5_Model(
+    (visual): RiceTransformerPretrainedModel(
+      (patch_embed): RicePatchEmbed(
+        (proj): Conv2d(3, 128, kernel_size=(14, 14), stride=(14, 14), bias=False)
+      )
+      (rotary_pos_emb): RiceRotaryEmbedding()
+      (pre_layernorm): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
+      (blocks): ModuleList(
+        (0-1): 2 x RiceBlock(
+          (norm1): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
+          (norm2): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
+          (attn): RiceSdpaAttention(
+            (qkv): Linear(in_features=128, out_features=384, bias=True)
+            (proj): Linear(in_features=128, out_features=128, bias=True)
+          )
+          (mlp): RiceMlp(
+            (fc1): Linear(in_features=128, out_features=256, bias=True)
+            (act): GELUActivation()
+            (fc2): Linear(in_features=256, out_features=128, bias=True)
+          )
+        )
+      )
+      (merger): RicePatchMerger(
+        (ln_q): LayerNorm((128,), eps=1e-05, elementwise_affine=True)
+        (mlp): Sequential(
+          (0): Linear(in_features=512, out_features=512, bias=True)
+          (1): GELU(approximate='none')
+          (2): Linear(in_features=512, out_features=8, bias=True)
+        )
+      )
+    )
+    (language_model): LLaVAOneVision1_5_TextModel(
+      (embed_tokens): Embedding(151936, 8)
+      (layers): ModuleList(
+        (0-1): 2 x LLaVAOneVision1_5_DecoderLayer(
+          (self_attn): LLaVAOneVision1_5_SdpaAttention(
+            (q_proj): Linear(in_features=8, out_features=256, bias=False)
+            (k_proj): Linear(in_features=8, out_features=128, bias=False)
+            (v_proj): Linear(in_features=8, out_features=128, bias=False)
+            (o_proj): Linear(in_features=256, out_features=8, bias=False)
+            (q_norm): LLaVAOneVision1_5_RMSNorm((32,), eps=1e-06)
+            (k_norm): LLaVAOneVision1_5_RMSNorm((32,), eps=1e-06)
+          )
+          (mlp): LLaVAOneVision1_5_MLP(
+            (gate_proj): Linear(in_features=8, out_features=64, bias=False)
+            (up_proj): Linear(in_features=8, out_features=64, bias=False)
+            (down_proj): Linear(in_features=64, out_features=8, bias=False)
+            (act_fn): SiLU()
+          )
+          (input_layernorm): LLaVAOneVision1_5_RMSNorm((8,), eps=1e-06)
+          (post_attention_layernorm): LLaVAOneVision1_5_RMSNorm((8,), eps=1e-06)
+        )
+      )
+      (norm): LLaVAOneVision1_5_RMSNorm((8,), eps=1e-06)
+      (rotary_emb): LLaVAOneVision1_5_RotaryEmbedding()
+    )
+  )
+  (lm_head): Linear(in_features=8, out_features=151936, bias=False)
+)
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "LLaVAOneVision1_5_ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "lmms-lab/LLaVA-OneVision-1.5-8B-Instruct--configuration_llavaonevision1_5.Llavaonevision1_5Config",
+    "AutoModel": "lmms-lab/LLaVA-OneVision-1.5-8B-Instruct--modeling_llavaonevision1_5.LLaVAOneVision1_5_ForConditionalGeneration",
+    "AutoModelForCausalLM": "lmms-lab/LLaVA-OneVision-1.5-8B-Instruct--modeling_llavaonevision1_5.LLaVAOneVision1_5_ForConditionalGeneration"
+  },
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "llavaonevision1_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 32,
+    "hidden_act": "silu",
+    "hidden_size": 8,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 2,
+    "model_type": "LLaVAOneVision1_5_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vocab_size": 151936
+  },
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 2,
+    "embed_dim": 128,
+    "hidden_act": "gelu",
+    "hidden_size": 128,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 256,
+    "layer_norm_eps": 1e-05,
+    "model_type": "rice_vit",
+    "num_heads": 4,
+    "num_hidden_layers": 2,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 1,
+    "text_hidden_size": 8
+  },
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.57.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4632ff8b43894a59833aa331b6a02aacc89b83b53dd3db0a0906f4414d6313
+size 6114256

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 3240000,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 3240000,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 3240000,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 3240000,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}