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

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 %}

compressed_config.json

@@ -0,0 +1,28 @@
+{
+  "format": "mindpipe_hf_save_pretrained_debug",
+  "algorithm": "splitquant",
+  "model_path": "/mnt/82_store/LLM-weights/Qwen2.5-VL-7B-Instruct",
+  "result_dir": "/mnt/82_store/wxx/HWQuant/Mindpipe/results/Qwen2.5-VL-7B-Instruct/splitquant/splitquant_w8a8_q16k16v16_seq512",
+  "weight_bits": 8,
+  "activation_bits": 8,
+  "sequence_length": 512,
+  "group_size": 128,
+  "output_dir": "/mnt/82_store/wxx/HWQuant/Mindpipe/tmp_hf_save/Qwen2.5-VL-7B-Instruct-SplitQuant-w8a8g128/_pre_save_workflow",
+  "pre_save_metrics": {
+    "perplexity": 11.440711999124886,
+    "evaluation_dataset": "wikitext2",
+    "sequence_length": 512,
+    "evaluated_chunks": 4,
+    "batch_size": 1,
+    "elapsed_seconds": 2.33213147521019,
+    "tokens_per_second": 876.4514444091445,
+    "model_path": "/mnt/82_store/LLM-weights/Qwen2.5-VL-7B-Instruct",
+    "quantization_algorithm": "splitquant",
+    "weight_bits": 8,
+    "activation_bits": 8,
+    "device": "cuda:0",
+    "dtype": "float16",
+    "artifacts_path": "artifacts.json"
+  },
+  "load_note": "Use MindPipe to rebuild the compression structure before loading the HF state dict."
+}

config.json

@@ -0,0 +1,101 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "dtype": "float16",
+  "image_token_id": 151655,
+  "model_type": "qwen2_5_vl",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "float16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_theta": 1000000.0,
+      "rope_type": "default",
+      "type": "mrope"
+    },
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.2",
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float16",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654
+}

extra_artifacts/splitquant_parameters.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c95531b7d4d15411f4952edc96f2580492c197ff0a3351a7acbcf6d9a13e7a1
+size 1172464535

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": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "5.5.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0300cebccb4df729ed71a9a54648e359286d73263f7a3b77d3be6d801c36cb83
+size 17751042936

processor_config.json

@@ -0,0 +1,59 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

reload_metrics.json

@@ -0,0 +1,32 @@
+{
+  "perplexity": 11.440711999124886,
+  "evaluation_dataset": "wikitext2",
+  "sequence_length": 512,
+  "evaluated_chunks": 4,
+  "batch_size": 1,
+  "elapsed_seconds": 2.3610186986625195,
+  "tokens_per_second": 865.7280017129447,
+  "ppl_comparison": {
+    "checked": true,
+    "passed": true,
+    "pre_save_ppl": 11.440711999124886,
+    "reload_ppl": 11.440711999124886,
+    "abs_diff": 0.0,
+    "rel_diff": 0.0,
+    "abs_tol": 0.0001,
+    "rel_tol": 1e-05
+  },
+  "original_ppl_comparison": {
+    "checked": true,
+    "passed": false,
+    "original_result_ppl": 10.96408460299306,
+    "pre_save_ppl": 11.440711999124886,
+    "reload_ppl": 11.440711999124886,
+    "pre_abs_diff": 0.4766273961318266,
+    "pre_rel_diff": 0.04347169995402199,
+    "reload_abs_diff": 0.4766273961318266,
+    "reload_rel_diff": 0.04347169995402199,
+    "abs_tol": 0.0001,
+    "rel_tol": 1e-05
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}