Upload folder using huggingface_hub

.gitattributes

@@ -67,3 +67,4 @@ qwen25-1p5b__gptq__wikitext2__n32__s0/tokenizer.json filter=lfs diff=lfs merge=l
 qwen25-1p5b__gptq__wikitext2__n32__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__wikitext2__n32__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__wikitext2__n512__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__wikitext2__n512__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__wikitext2__n512__s1/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T19:25:29.499151+00:00

qwen25-1p5b__gptq__wikitext2__n512__s1/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 %}

qwen25-1p5b__gptq__wikitext2__n512__s1/config.json

@@ -0,0 +1,108 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "format": "gptq",
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": false,
+      "auto_forward_data_parallel": true,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.01,
+      "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_60jao5c8",
+      "pack_impl": "cpu",
+      "quantizer": [
+        "gptqmodel:7.3.2"
+      ],
+      "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": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen25-1p5b__gptq__wikitext2__n512__s1/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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.14.1"
+}

qwen25-1p5b__gptq__wikitext2__n512__s1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e5fbdf1d6222c7f1a798626cd17c6a592839e9fc35315d9a7562234c7b885a
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n512__s1/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000077330,0.01000,4.028
+0,self_attn.v_proj,0.0000001288,0.01000,4.053
+0,self_attn.k_proj,0.0000010927,0.01000,4.064
+0,self_attn.o_proj,0.0000002962,0.01000,0.536
+0,mlp.gate_proj,0.0000033171,0.01000,2.139
+0,mlp.up_proj,0.0000022771,0.01000,2.153
+0,mlp.down_proj,0.0000005440,0.01000,3.277
+1,self_attn.k_proj,0.0000003561,0.01000,3.972
+1,self_attn.v_proj,0.0000000795,0.01000,3.975
+1,self_attn.q_proj,0.0000011958,0.01000,4.019
+1,self_attn.o_proj,0.0000001136,0.01000,0.548
+1,mlp.up_proj,0.0000724101,0.01000,2.248
+1,mlp.gate_proj,0.0000889673,0.01000,2.262
+1,mlp.down_proj,0.0000031968,0.01000,3.329
+2,self_attn.q_proj,0.0000036540,0.01000,3.975
+2,self_attn.v_proj,0.0000003290,0.01000,4.043
+2,self_attn.k_proj,0.0000007985,0.01000,4.069
+2,self_attn.o_proj,0.0000002166,0.01000,0.553
+2,mlp.gate_proj,0.0000775064,0.01000,2.269
+2,mlp.up_proj,0.0000484661,0.01000,2.290
+2,mlp.down_proj,0.0000068192,0.01000,3.299
+3,self_attn.k_proj,0.0000007992,0.01000,4.067
+3,self_attn.q_proj,0.0000037043,0.01000,4.098
+3,self_attn.v_proj,0.0000004271,0.01000,4.123
+3,self_attn.o_proj,0.0000003124,0.01000,0.546
+3,mlp.gate_proj,0.0000647282,0.01000,2.265
+3,mlp.up_proj,0.0000346400,0.01000,2.275
+3,mlp.down_proj,0.0000019870,0.01000,3.311
+4,self_attn.v_proj,0.0000006253,0.01000,3.949
+4,self_attn.q_proj,0.0000049324,0.01000,3.955
+4,self_attn.k_proj,0.0000009949,0.01000,3.975
+4,self_attn.o_proj,0.0000004293,0.01000,0.538
+4,mlp.gate_proj,0.0000460337,0.01000,2.154
+4,mlp.up_proj,0.0000279316,0.01000,2.171
+4,mlp.down_proj,0.0000025262,0.01000,3.278
+5,self_attn.k_proj,0.0000011045,0.01000,4.218
+5,self_attn.v_proj,0.0000007890,0.01000,4.249
+5,self_attn.q_proj,0.0000051092,0.01000,4.272
+5,self_attn.o_proj,0.0000006089,0.01000,0.543
+5,mlp.up_proj,0.0000590043,0.01000,2.360
+5,mlp.gate_proj,0.0000906238,0.01000,2.364
+5,mlp.down_proj,0.0000021864,0.01000,3.287
+6,self_attn.q_proj,0.0000066512,0.01000,4.162
+6,self_attn.v_proj,0.0000005430,0.01000,4.210
+6,self_attn.k_proj,0.0000014485,0.01000,4.222
+6,self_attn.o_proj,0.0000003226,0.01000,0.549
+6,mlp.up_proj,0.0000229353,0.01000,2.249
+6,mlp.gate_proj,0.0000275070,0.01000,2.264
+6,mlp.down_proj,0.0000023494,0.01000,3.308
+7,self_attn.k_proj,0.0000006360,0.01000,4.191
+7,self_attn.q_proj,0.0000030438,0.01000,4.217
+7,self_attn.v_proj,0.0000004572,0.01000,4.231
+7,self_attn.o_proj,0.0000004418,0.01000,0.548
+7,mlp.gate_proj,0.0000226755,0.01000,2.297
+7,mlp.up_proj,0.0000214142,0.01000,2.316
+7,mlp.down_proj,0.0000023737,0.01000,3.321
+8,self_attn.v_proj,0.0000005984,0.01000,4.136
+8,self_attn.q_proj,0.0000065265,0.01000,4.162
+8,self_attn.k_proj,0.0000011549,0.01000,4.169
+8,self_attn.o_proj,0.0000006129,0.01000,0.540
+8,mlp.up_proj,0.0000207475,0.01000,2.359
+8,mlp.gate_proj,0.0000225745,0.01000,2.368
+8,mlp.down_proj,0.0000021815,0.01000,3.298
+9,self_attn.k_proj,0.0000010223,0.01000,4.134
+9,self_attn.v_proj,0.0000005248,0.01000,4.145
+9,self_attn.q_proj,0.0000047674,0.01000,4.176
+9,self_attn.o_proj,0.0000005235,0.01000,0.543
+9,mlp.up_proj,0.0000194149,0.01000,2.169
+9,mlp.gate_proj,0.0000200467,0.01000,2.195
+9,mlp.down_proj,0.0000020366,0.01000,3.314
+10,self_attn.q_proj,0.0000051017,0.01000,4.160
+10,self_attn.v_proj,0.0000008157,0.01000,4.201
+10,self_attn.k_proj,0.0000010125,0.01000,4.218
+10,self_attn.o_proj,0.0000008479,0.01000,0.547
+10,mlp.gate_proj,0.0000190881,0.01000,2.326
+10,mlp.up_proj,0.0000180675,0.01000,2.328
+10,mlp.down_proj,0.0000017886,0.01000,3.334
+11,self_attn.q_proj,0.0000047119,0.01000,4.073
+11,self_attn.k_proj,0.0000009423,0.01000,4.095
+11,self_attn.v_proj,0.0000006212,0.01000,4.121
+11,self_attn.o_proj,0.0000007774,0.01000,0.540
+11,mlp.up_proj,0.0000160563,0.01000,2.219
+11,mlp.gate_proj,0.0000181036,0.01000,2.220
+11,mlp.down_proj,0.0000014661,0.01000,3.341
+12,self_attn.v_proj,0.0000006052,0.01000,4.036
+12,self_attn.q_proj,0.0000058220,0.01000,4.069
+12,self_attn.k_proj,0.0000012392,0.01000,4.079
+12,self_attn.o_proj,0.0000006438,0.01000,0.553
+12,mlp.gate_proj,0.0000167377,0.01000,2.299
+12,mlp.up_proj,0.0000155442,0.01000,2.314
+12,mlp.down_proj,0.0000015434,0.01000,3.339
+13,self_attn.q_proj,0.0000035037,0.01000,4.482
+13,self_attn.v_proj,0.0000004650,0.01000,4.509
+13,self_attn.k_proj,0.0000007093,0.01000,4.512
+13,self_attn.o_proj,0.0000007359,0.01000,0.544
+13,mlp.up_proj,0.0000148619,0.01000,2.314
+13,mlp.gate_proj,0.0000154341,0.01000,2.330
+13,mlp.down_proj,0.0000013372,0.01000,3.293
+14,self_attn.q_proj,0.0000080075,0.01000,4.058
+14,self_attn.v_proj,0.0000008156,0.01000,4.098
+14,self_attn.k_proj,0.0000012209,0.01000,4.121
+14,self_attn.o_proj,0.0000006872,0.01000,0.538
+14,mlp.gate_proj,0.0000164441,0.01000,2.302
+14,mlp.up_proj,0.0000168972,0.01000,2.310
+14,mlp.down_proj,0.0000016339,0.01000,3.304
+15,self_attn.q_proj,0.0000107706,0.01000,4.222
+15,self_attn.k_proj,0.0000009130,0.01000,4.253
+15,self_attn.v_proj,0.0000008004,0.01000,4.269
+15,self_attn.o_proj,0.0000009365,0.01000,0.543
+15,mlp.gate_proj,0.0000145138,0.01000,2.261
+15,mlp.up_proj,0.0000139205,0.01000,2.279
+15,mlp.down_proj,0.0000013035,0.01000,3.276
+16,self_attn.v_proj,0.0000008812,0.01000,3.889
+16,self_attn.q_proj,0.0000062962,0.01000,3.923
+16,self_attn.k_proj,0.0000011722,0.01000,3.931
+16,self_attn.o_proj,0.0000007443,0.01000,0.542
+16,mlp.gate_proj,0.0000162058,0.01000,2.212
+16,mlp.up_proj,0.0000160050,0.01000,2.223
+16,mlp.down_proj,0.0000015431,0.01000,3.276
+17,self_attn.k_proj,0.0000007092,0.01000,4.211
+17,self_attn.v_proj,0.0000011527,0.01000,4.216
+17,self_attn.q_proj,0.0000058229,0.01000,4.249
+17,self_attn.o_proj,0.0000006843,0.01000,0.542
+17,mlp.gate_proj,0.0000156584,0.01000,2.218
+17,mlp.up_proj,0.0000156905,0.01000,2.230
+17,mlp.down_proj,0.0000017380,0.01000,3.321
+18,self_attn.q_proj,0.0000045721,0.01000,4.072
+18,self_attn.v_proj,0.0000007688,0.01000,4.088
+18,self_attn.k_proj,0.0000007872,0.01000,4.117
+18,self_attn.o_proj,0.0000009582,0.01000,0.547
+18,mlp.gate_proj,0.0000166070,0.01000,2.233
+18,mlp.up_proj,0.0000163980,0.01000,2.250
+18,mlp.down_proj,0.0000021996,0.01000,3.306
+19,self_attn.k_proj,0.0000009033,0.01000,4.089
+19,self_attn.q_proj,0.0000063382,0.01000,4.118
+19,self_attn.v_proj,0.0000015799,0.01000,4.137
+19,self_attn.o_proj,0.0000009348,0.01000,0.540
+19,mlp.up_proj,0.0000194921,0.01000,2.271
+19,mlp.gate_proj,0.0000182135,0.01000,2.288
+19,mlp.down_proj,0.0000038680,0.01000,3.304
+20,self_attn.v_proj,0.0000021120,0.01000,3.751
+20,self_attn.q_proj,0.0000068275,0.01000,3.791
+20,self_attn.k_proj,0.0000010585,0.01000,3.800
+20,self_attn.o_proj,0.0000016201,0.01000,0.538
+20,mlp.gate_proj,0.0000212923,0.01000,2.134
+20,mlp.up_proj,0.0000218030,0.01000,2.141
+20,mlp.down_proj,0.0000039311,0.01000,3.300
+21,self_attn.v_proj,0.0000019285,0.01000,3.892
+21,self_attn.k_proj,0.0000010491,0.01000,3.906
+21,self_attn.q_proj,0.0000073233,0.01000,3.946
+21,self_attn.o_proj,0.0000011466,0.01000,0.553
+21,mlp.up_proj,0.0000305160,0.01000,2.096
+21,mlp.gate_proj,0.0000300531,0.01000,2.112
+21,mlp.down_proj,0.0000068656,0.01000,3.277
+22,self_attn.q_proj,0.0000069531,0.01000,4.081
+22,self_attn.v_proj,0.0000025244,0.01000,4.130
+22,self_attn.k_proj,0.0000012271,0.01000,4.158
+22,self_attn.o_proj,0.0000016307,0.01000,0.544
+22,mlp.up_proj,0.0000363417,0.01000,2.336
+22,mlp.gate_proj,0.0000361885,0.01000,2.340
+22,mlp.down_proj,0.0000098906,0.01000,3.308
+23,self_attn.q_proj,0.0000092536,0.01000,4.183
+23,self_attn.k_proj,0.0000014433,0.01000,4.210
+23,self_attn.v_proj,0.0000033882,0.01000,4.231
+23,self_attn.o_proj,0.0000015257,0.01000,0.547
+23,mlp.up_proj,0.0000416835,0.01000,2.169
+23,mlp.gate_proj,0.0000397292,0.01000,2.184
+23,mlp.down_proj,0.0000141283,0.01000,3.290
+24,self_attn.q_proj,0.0000100452,0.01000,4.317
+24,self_attn.k_proj,0.0000016384,0.01000,4.341
+24,self_attn.v_proj,0.0000070202,0.01000,4.347
+24,self_attn.o_proj,0.0000020350,0.01000,0.545
+24,mlp.gate_proj,0.0000443096,0.01000,2.359
+24,mlp.up_proj,0.0000476014,0.01000,2.373
+24,mlp.down_proj,0.0000175060,0.01000,3.280
+25,self_attn.k_proj,0.0000018915,0.01000,3.976
+25,self_attn.v_proj,0.0000116649,0.01000,3.995
+25,self_attn.q_proj,0.0000106701,0.01000,4.021
+25,self_attn.o_proj,0.0000047635,0.01000,0.535
+25,mlp.up_proj,0.0000524923,0.01000,2.175
+25,mlp.gate_proj,0.0000455820,0.01000,2.191
+25,mlp.down_proj,0.0000234537,0.01000,3.305
+26,self_attn.q_proj,0.0000117508,0.01000,4.033
+26,self_attn.v_proj,0.0000137001,0.01000,4.061
+26,self_attn.k_proj,0.0000018237,0.01000,4.088
+26,self_attn.o_proj,0.0000025624,0.01000,0.552
+26,mlp.gate_proj,0.0000453298,0.01000,2.094
+26,mlp.up_proj,0.0000543044,0.01000,2.112
+26,mlp.down_proj,0.0000345982,0.01000,3.283
+27,self_attn.q_proj,0.0000123822,0.01000,3.914
+27,self_attn.k_proj,0.0000019889,0.01000,3.914
+27,self_attn.v_proj,0.0000145450,0.01000,3.948
+27,self_attn.o_proj,0.0000095030,0.01000,0.546
+27,mlp.up_proj,0.0000644787,0.01000,2.214
+27,mlp.gate_proj,0.0000618511,0.01000,2.227
+27,mlp.down_proj,0.0000463635,0.01000,3.294

qwen25-1p5b__gptq__wikitext2__n512__s1/quantize_config.json

@@ -0,0 +1,47 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": true,
+  "lm_head": false,
+  "method": "gptq",
+  "quant_method": "gptq",
+  "format": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:7.3.2"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "gptaq": null,
+    "foem": null,
+    "act_group_aware": false,
+    "fallback": {
+      "strategy": "rtn",
+      "threshold": "0.5%",
+      "smooth": null
+    },
+    "offload_to_disk": true,
+    "offload_to_disk_path": "/tmp/gptqmodel_60jao5c8",
+    "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
+}

qwen25-1p5b__gptq__wikitext2__n512__s1/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n512__s1/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": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}