初始化项目，由ModelHub XC社区提供模型

Model: AArrouet/Qwen3-1.7B-QuantizedGPTQ Source: Original Platform
2026-07-10 04:07:10 +08:00
commit 64bcf80bb0
10 changed files with 727 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "format": "gptq",
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": true,
+      "auto_forward_data_parallel": true,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.05,
+      "dense_vram_strategy": "exclusive",
+      "dense_vram_strategy_devices": null,
+      "fallback": {
+        "smooth": null,
+        "strategy": "rtn",
+        "threshold": "0.5%"
+      },
+      "foem": null,
+      "gc_mode": "interval",
+      "gptaq": null,
+      "hessian": {
+        "chunk_bytes": null,
+        "chunk_size": null,
+        "staging_dtype": "float32"
+      },
+      "mock_quantization": false,
+      "moe_vram_strategy": "exclusive",
+      "moe_vram_strategy_devices": null,
+      "mse": 0.0,
+      "offload_to_disk": true,
+      "offload_to_disk_path": "/tmp/gptqmodel_xoo8eybm",
+      "pack_impl": "cpu",
+      "quantizer": [
+        "gptqmodel:7.0.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "wait_for_submodule_finalizers": false
+    },
+    "method": "gptq",
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.9.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91981dea93edbe4bb4040777acb2c9da3cae76d2ffde76e43a9f42c27ec9787
+size 1356910240
--- a/quant_log.csv
+++ b/quant_log.csv
@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000008398,0.05000,3.626
+0,self_attn.k_proj,0.0000009675,0.05000,3.894
+0,self_attn.q_proj,0.0000020267,0.05000,3.921
+0,self_attn.o_proj,0.0000021352,0.05000,0.764
+0,mlp.gate_proj,0.0000197972,0.05000,2.009
+0,mlp.up_proj,0.0000128524,0.05000,2.049
+0,mlp.down_proj,0.0000043071,0.05000,2.590
+1,self_attn.v_proj,0.0000006024,0.05000,4.008
+1,self_attn.q_proj,0.0000012551,0.05000,4.125
+1,self_attn.k_proj,0.0000006186,0.05000,4.172
+1,self_attn.o_proj,0.0000006818,0.05000,1.591
+1,mlp.gate_proj,0.0002898050,0.05000,2.585
+1,mlp.up_proj,0.0001188112,0.05000,2.701
+1,mlp.down_proj,0.0000065027,0.05000,3.925
+2,self_attn.q_proj,0.0000027077,0.05000,4.020
+2,self_attn.v_proj,0.0000012527,0.05000,4.084
+2,self_attn.k_proj,0.0000012390,0.05000,4.077
+2,self_attn.o_proj,0.0000011485,0.05000,1.080
+2,mlp.gate_proj,0.0002410469,0.05000,1.939
+2,mlp.up_proj,0.0000994754,0.05000,1.991
+2,mlp.down_proj,0.0052349447,0.05000,2.563
+3,self_attn.k_proj,0.0000090444,0.05000,3.422
+3,self_attn.q_proj,0.0000174781,0.05000,3.473
+3,self_attn.v_proj,0.0000092185,0.05000,3.435
+3,self_attn.o_proj,0.0000022031,0.05000,1.213
+3,mlp.gate_proj,0.0002953793,0.05000,2.184
+3,mlp.up_proj,0.0001297567,0.05000,2.222
+3,mlp.down_proj,0.0000122510,0.05000,2.570
+4,self_attn.v_proj,0.0000088477,0.05000,3.349
+4,self_attn.k_proj,0.0000081188,0.05000,3.382
+4,self_attn.q_proj,0.0000165550,0.05000,3.424
+4,self_attn.o_proj,0.0000034003,0.05000,0.853
+4,mlp.gate_proj,0.0002626366,0.05000,1.896
+4,mlp.up_proj,0.0001246561,0.05000,1.932
+4,mlp.down_proj,0.0000179021,0.05000,2.540
+5,self_attn.v_proj,0.0000134986,0.05000,3.336
+5,self_attn.k_proj,0.0000108491,0.05000,3.354
+5,self_attn.q_proj,0.0000251860,0.05000,3.433
+5,self_attn.o_proj,0.0000050791,0.05000,0.768
+5,mlp.gate_proj,0.0001303575,0.05000,2.189
+5,mlp.up_proj,0.0000894665,0.05000,2.193
+5,mlp.down_proj,0.0000214953,0.05000,3.112
+6,self_attn.k_proj,0.0000100134,0.05000,3.482
+6,self_attn.v_proj,0.0000103902,0.05000,3.516
+6,self_attn.q_proj,0.0000207434,0.05000,3.553
+6,self_attn.o_proj,0.0000053416,0.05000,0.858
+6,mlp.up_proj,0.0001180585,0.05000,2.169
+6,mlp.gate_proj,0.0001675667,0.05000,2.197
+6,mlp.down_proj,0.0000290387,0.05000,2.959
+7,self_attn.q_proj,0.0000449065,0.05000,3.457
+7,self_attn.k_proj,0.0000192821,0.05000,3.492
+7,self_attn.v_proj,0.0000234869,0.05000,3.489
+7,self_attn.o_proj,0.0000085582,0.05000,0.825
+7,mlp.gate_proj,0.0002227390,0.05000,2.001
+7,mlp.up_proj,0.0001480158,0.05000,2.032
+7,mlp.down_proj,0.0000303750,0.05000,2.681
+8,self_attn.q_proj,0.0000543600,0.05000,3.252
+8,self_attn.k_proj,0.0000271505,0.05000,3.266
+8,self_attn.v_proj,0.0000257857,0.05000,3.332
+8,self_attn.o_proj,0.0000072512,0.05000,0.798
+8,mlp.up_proj,0.0001467434,0.05000,1.923
+8,mlp.gate_proj,0.0001986378,0.05000,1.961
+8,mlp.down_proj,0.0000381824,0.05000,2.596
+9,self_attn.k_proj,0.0000496773,0.05000,3.310
+9,self_attn.q_proj,0.0001079280,0.05000,3.415
+9,self_attn.v_proj,0.0000501777,0.05000,3.450
+9,self_attn.o_proj,0.0000210494,0.05000,0.810
+9,mlp.up_proj,0.0001489672,0.05000,2.018
+9,mlp.gate_proj,0.0001845221,0.05000,2.074
+9,mlp.down_proj,0.0000494351,0.05000,2.579
+10,self_attn.k_proj,0.0000368918,0.05000,3.372
+10,self_attn.v_proj,0.0000397413,0.05000,3.451
+10,self_attn.q_proj,0.0000817303,0.05000,3.489
+10,self_attn.o_proj,0.0000214367,0.05000,0.834
+10,mlp.gate_proj,0.0001894916,0.05000,2.030
+10,mlp.up_proj,0.0001573987,0.05000,2.045
+10,mlp.down_proj,0.0000817361,0.05000,2.763
+11,self_attn.q_proj,0.0001917333,0.05000,3.454
+11,self_attn.k_proj,0.0000857933,0.05000,3.472
+11,self_attn.v_proj,0.0000807375,0.05000,3.529
+11,self_attn.o_proj,0.0000535566,0.05000,1.224
+11,mlp.gate_proj,0.0001578729,0.05000,1.960
+11,mlp.up_proj,0.0001494230,0.05000,2.039
+11,mlp.down_proj,0.0000893180,0.05000,2.668
+12,self_attn.v_proj,0.0000763319,0.05000,3.301
+12,self_attn.k_proj,0.0000745997,0.05000,3.364
+12,self_attn.q_proj,0.0001640630,0.05000,3.380
+12,self_attn.o_proj,0.0000343813,0.05000,1.200
+12,mlp.up_proj,0.0001588971,0.05000,2.040
+12,mlp.gate_proj,0.0001566968,0.05000,2.088
+12,mlp.down_proj,0.0001093978,0.05000,2.760
+13,self_attn.q_proj,0.0002423986,0.05000,3.553
+13,self_attn.v_proj,0.0001063420,0.05000,3.661
+13,self_attn.k_proj,0.0000977330,0.05000,3.718
+13,self_attn.o_proj,0.0000535365,0.05000,0.863
+13,mlp.gate_proj,0.0001755430,0.05000,2.180
+13,mlp.up_proj,0.0001757205,0.05000,2.202
+13,mlp.down_proj,0.0001403776,0.05000,3.126
+14,self_attn.q_proj,0.0003975555,0.05000,3.663
+14,self_attn.k_proj,0.0001722038,0.05000,3.679
+14,self_attn.v_proj,0.0001753240,0.05000,3.693
+14,self_attn.o_proj,0.0000595465,0.05000,0.862
+14,mlp.gate_proj,0.0002011682,0.05000,2.305
+14,mlp.up_proj,0.0002059663,0.05000,2.407
+14,mlp.down_proj,0.0001984588,0.05000,3.394
+15,self_attn.q_proj,0.0008955670,0.05000,3.697
+15,self_attn.k_proj,0.0003116054,0.05000,3.737
+15,self_attn.v_proj,0.0004181195,0.05000,3.791
+15,self_attn.o_proj,0.0001117162,0.05000,0.872
+15,mlp.gate_proj,0.0002431306,0.05000,2.044
+15,mlp.up_proj,0.0002530560,0.05000,2.098
+15,mlp.down_proj,0.0003042576,0.05000,2.786
+16,self_attn.q_proj,0.0012468852,0.05000,3.625
+16,self_attn.v_proj,0.0004789103,0.05000,3.631
+16,self_attn.k_proj,0.0004600213,0.05000,3.666
+16,self_attn.o_proj,0.0001508937,0.05000,0.845
+16,mlp.up_proj,0.0003300065,0.05000,2.094
+16,mlp.gate_proj,0.0002871720,0.05000,2.138
+16,mlp.down_proj,0.0008724837,0.05000,2.769
+17,self_attn.k_proj,0.0012925876,0.05000,3.544
+17,self_attn.q_proj,0.0035529846,0.05000,3.629
+17,self_attn.v_proj,0.0016027982,0.05000,3.645
+17,self_attn.o_proj,0.0004630940,0.05000,0.837
+17,mlp.up_proj,0.0005086830,0.05000,2.186
+17,mlp.gate_proj,0.0004439794,0.05000,2.247
+17,mlp.down_proj,0.0012258750,0.05000,2.896
+18,self_attn.q_proj,0.0045345503,0.05000,3.490
+18,self_attn.k_proj,0.0015577570,0.05000,3.584
+18,self_attn.v_proj,0.0018117692,0.05000,3.587
+18,self_attn.o_proj,0.0003796638,0.05000,0.831
+18,mlp.up_proj,0.0006954494,0.05000,2.228
+18,mlp.gate_proj,0.0006154586,0.05000,2.271
+18,mlp.down_proj,0.0019921769,0.05000,2.766
+19,self_attn.q_proj,0.0082794433,0.05000,3.540
+19,self_attn.v_proj,0.0035734420,0.05000,3.562
+19,self_attn.k_proj,0.0027089883,0.05000,3.621
+19,self_attn.o_proj,0.0007345936,0.05000,0.883
+19,mlp.up_proj,0.0010398286,0.05000,2.173
+19,mlp.gate_proj,0.0009062103,0.05000,2.236
+19,mlp.down_proj,0.0047007723,0.05000,2.741
+20,self_attn.k_proj,0.0049409603,0.05000,3.462
+20,self_attn.v_proj,0.0062833487,0.05000,3.546
+20,self_attn.q_proj,0.0141710609,0.05000,3.616
+20,self_attn.o_proj,0.0011029547,0.05000,0.901
+20,mlp.up_proj,0.0013506484,0.05000,2.137
+20,mlp.gate_proj,0.0011972403,0.05000,2.187
+20,mlp.down_proj,0.0063867690,0.05000,2.863
+21,self_attn.v_proj,0.0098904379,0.05000,3.438
+21,self_attn.k_proj,0.0073228886,0.05000,3.531
+21,self_attn.q_proj,0.0200067527,0.05000,3.600
+21,self_attn.o_proj,0.0015405809,0.05000,0.902
+21,mlp.gate_proj,0.0014323293,0.05000,2.231
+21,mlp.up_proj,0.0016531138,0.05000,2.248
+21,mlp.down_proj,0.0089285798,0.05000,2.775
+22,self_attn.k_proj,0.0102904142,0.05000,3.497
+22,self_attn.q_proj,0.0279091075,0.05000,3.558
+22,self_attn.v_proj,0.0136463096,0.05000,3.561
+22,self_attn.o_proj,0.0017626955,0.05000,0.875
+22,mlp.up_proj,0.0019068349,0.05000,2.061
+22,mlp.gate_proj,0.0016667122,0.05000,2.118
+22,mlp.down_proj,0.0102301358,0.05000,2.784
+23,self_attn.k_proj,0.0126362919,0.05000,3.470
+23,self_attn.v_proj,0.0155633528,0.05000,3.562
+23,self_attn.q_proj,0.0293295363,0.05000,3.648
+23,self_attn.o_proj,0.0018687698,0.05000,0.878
+23,mlp.gate_proj,0.0019935730,0.05000,2.148
+23,mlp.up_proj,0.0022690450,0.05000,2.207
+23,mlp.down_proj,0.0120860929,0.05000,2.854
+24,self_attn.q_proj,0.0559459186,0.05000,3.423
+24,self_attn.v_proj,0.0249366372,0.05000,3.485
+24,self_attn.k_proj,0.0213881481,0.05000,3.516
+24,self_attn.o_proj,0.0023866374,0.05000,1.135
+24,mlp.up_proj,0.0022699147,0.05000,2.120
+24,mlp.gate_proj,0.0019399213,0.05000,2.160
+24,mlp.down_proj,0.0147081203,0.05000,2.699
+25,self_attn.q_proj,0.0651313592,0.05000,3.340
+25,self_attn.v_proj,0.0362999953,0.05000,3.385
+25,self_attn.k_proj,0.0240991880,0.05000,3.424
+25,self_attn.o_proj,0.0027495860,0.05000,1.318
+25,mlp.up_proj,0.0022078746,0.05000,2.105
+25,mlp.gate_proj,0.0018362088,0.05000,2.142
+25,mlp.down_proj,0.0172555837,0.05000,2.694
+26,self_attn.v_proj,0.0339960720,0.05000,3.506
+26,self_attn.q_proj,0.0760382617,0.05000,3.565
+26,self_attn.k_proj,0.0228024484,0.05000,3.605
+26,self_attn.o_proj,0.0054717644,0.05000,1.536
+26,mlp.gate_proj,0.0018231207,0.05000,2.180
+26,mlp.up_proj,0.0021639906,0.05000,2.183
+26,mlp.down_proj,0.0193138215,0.05000,2.813
+27,self_attn.k_proj,0.0116609379,0.05000,3.489
+27,self_attn.v_proj,0.0142843226,0.05000,3.582
+27,self_attn.q_proj,0.0253722723,0.05000,3.648
+27,self_attn.o_proj,0.0031136294,0.05000,1.527
+27,mlp.up_proj,0.0031771694,0.05000,2.073
+27,mlp.gate_proj,0.0031102671,0.05000,2.147
+27,mlp.down_proj,0.0421205361,0.05000,2.798
--- a/quantize_config.json
+++ b/quantize_config.json
@@ -0,0 +1,47 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": false,
+  "lm_head": false,
+  "method": "gptq",
+  "quant_method": "gptq",
+  "format": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:7.0.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "gptaq": null,
+    "foem": null,
+    "act_group_aware": true,
+    "fallback": {
+      "strategy": "rtn",
+      "threshold": "0.5%",
+      "smooth": null
+    },
+    "offload_to_disk": true,
+    "offload_to_disk_path": "/tmp/gptqmodel_xoo8eybm",
+    "pack_impl": "cpu",
+    "gc_mode": "interval",
+    "wait_for_submodule_finalizers": false,
+    "auto_forward_data_parallel": true,
+    "dense_vram_strategy": "exclusive",
+    "dense_vram_strategy_devices": null,
+    "moe_vram_strategy": "exclusive",
+    "moe_vram_strategy_devices": null,
+    "mock_quantization": false,
+    "hessian": {
+      "chunk_size": null,
+      "chunk_bytes": null,
+      "staging_dtype": "float32"
+    }
+  },
+  "sym": true
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,31 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "_commit_hash": null
+}