Upload 9 files

.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

@@ -1,3 +1,36 @@
----
-license: mit
----
+---
+license: mit
+library_name: peft
+base_model: lmms-lab/llava-onevision-qwen2-7b-ov
+datasets:
+- wangyueqian/MMDuetIT
+language:
+- en
+tags:
+- llava-onevision
+- llava
+- multimodal
+- online video understanding
+- video understanding
+pipeline_tag: video-text-to-text
+---
+
+# MMDuet
+
+This is the model checkpoint of **MMDuet**, a VideoLLM you can interact with in a real-time manner while the video plays.
+
+## Model Details
+
+
+## Related Resources
+- **Github:** [MMDuet](https://github.com/yellow-binary-tree/MMDuet)
+- **Paper:** TODO
+- **Demo:** [Video Demo](https://www.youtube.com/watch?v=n1OybwhQvtk)
+- **Data:** [MMDuetIT](https://huggingface.co/datasets/wangyueqian/MMDuetIT)
+
+
+## Citation
+If you use this work in your research, please consider cite:
+```bibtex
+
+```

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-ov",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "connector",
+    "mm_projector",
+    "response_head",
+    "related_head"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "model\\.layers.*(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)$",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75040853d5e19b352df09d52bafc70e4efe74065dab7d4766b417cbbfdfa73c
+size 114783784

added_tokens.json

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

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "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 sha256:32e8f623d8dce60b5a93496ec810434ef744287ac041cf2c6032743a3578baa5
+size 11418450

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": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{{ bos_token + 'system\n' + messages[0]['content'] + eos_token}}{% set messages = messages[1:] %}{% endif %}{% for i in range(messages | length) %}{% set message = messages[i] %}{% if message['role'] == 'user' %}{% if add_stream_query_prompt %}{{ eos_token + '\n' + bos_token + 'user\n' + message['content'] + eos_token }}{% else %}{{ '\n' + bos_token + 'user\n' + message['content'] + eos_token }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n' + bos_token + 'assistant\n' + message['content'] + eos_token }}{% elif message['role'] == 'stream' and message['num_frames'] > 0 %}{{ '\n' + bos_token + 'stream\n' + ''.join([49 * '<image>'] * message['num_frames']) + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n' + bos_token + 'assistant\n' }}{% elif add_stream_prompt %}{{ '\n' + bos_token + 'stream\n' }}{% elif add_stream_generation_prompt %}{{ eos_token + '\n' + bos_token + 'assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}