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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

compressed_config.json

@@ -0,0 +1,28 @@
+{
+  "format": "mindpipe_hf_save_pretrained_debug",
+  "algorithm": "splitquant",
+  "model_path": "/mnt/82_store/LLM-weights/Qwen2.5-7B-Instruct",
+  "result_dir": "/mnt/82_store/wxx/HWQuant/Mindpipe/results/Qwen2.5-7B-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/Qwen2.5-7B-Instruct-SplitQuant-w8a8g128/_pre_save_workflow",
+  "pre_save_metrics": {
+    "perplexity": 9.376587445576774,
+    "evaluation_dataset": "wikitext2",
+    "sequence_length": 512,
+    "evaluated_chunks": 4,
+    "batch_size": 1,
+    "elapsed_seconds": 2.2659640507772565,
+    "tokens_per_second": 902.0443194140173,
+    "model_path": "/mnt/82_store/LLM-weights/Qwen2.5-7B-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 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "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": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

extra_artifacts/splitquant_parameters.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17f8f584a2e569a689afd748cfeb4e764979dfcde2c88857f13bbfa6dc3f0e0
+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": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.5.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78f91372bd0830e215c1faa0c8a1e2f711cdaaf8f144eeb4c177727b38d8fdd
+size 16397696320

reload_metrics.json

@@ -0,0 +1,32 @@
+{
+  "perplexity": 9.376587445576774,
+  "evaluation_dataset": "wikitext2",
+  "sequence_length": 512,
+  "evaluated_chunks": 4,
+  "batch_size": 1,
+  "elapsed_seconds": 1.8734785178676248,
+  "tokens_per_second": 1091.0186482023082,
+  "ppl_comparison": {
+    "checked": true,
+    "passed": true,
+    "pre_save_ppl": 9.376587445576774,
+    "reload_ppl": 9.376587445576774,
+    "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": 9.426495043879168,
+    "pre_save_ppl": 9.376587445576774,
+    "reload_ppl": 9.376587445576774,
+    "pre_abs_diff": 0.04990759830239355,
+    "pre_rel_diff": 0.005294396068748762,
+    "reload_abs_diff": 0.04990759830239355,
+    "reload_rel_diff": 0.005294396068748762,
+    "abs_tol": 0.0001,
+    "rel_tol": 1e-05
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
+size 11422166

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}