Upload folder using huggingface_hub

.gitattributes

@@ -62,3 +62,4 @@ qwen25-1p5b__gptq__openhermes__n512__s0/tokenizer.json filter=lfs diff=lfs merge
 qwen25-1p5b__gptq__openhermes__n512__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__openhermes__n512__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__wikitext2__n128__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__wikitext2__n128__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__wikitext2__n128__s2/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T18:53:26.174764+00:00

qwen25-1p5b__gptq__wikitext2__n128__s2/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__n128__s2/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_iz40g1x9",
+      "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__n128__s2/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__n128__s2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4badf22c12351e47db49cdb87cb216ce8d181544d8d166275c3b6a4022037a2
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n128__s2/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000004981,0.01000,4.145
+0,self_attn.q_proj,0.0000298573,0.01000,4.157
+0,self_attn.k_proj,0.0000042270,0.01000,4.173
+0,self_attn.o_proj,0.0000011636,0.01000,0.536
+0,mlp.gate_proj,0.0000131068,0.01000,2.295
+0,mlp.up_proj,0.0000089822,0.01000,2.307
+0,mlp.down_proj,0.0000020434,0.01000,3.305
+1,self_attn.k_proj,0.0000014026,0.01000,4.318
+1,self_attn.q_proj,0.0000046963,0.01000,4.350
+1,self_attn.v_proj,0.0000003134,0.01000,4.347
+1,self_attn.o_proj,0.0000004487,0.01000,0.542
+1,mlp.up_proj,0.0002852730,0.01000,2.366
+1,mlp.gate_proj,0.0003501339,0.01000,2.378
+1,mlp.down_proj,0.0000123004,0.01000,3.333
+2,self_attn.q_proj,0.0000143533,0.01000,4.470
+2,self_attn.k_proj,0.0000031341,0.01000,4.542
+2,self_attn.v_proj,0.0000012906,0.01000,4.545
+2,self_attn.o_proj,0.0000008440,0.01000,0.552
+2,mlp.gate_proj,0.0003043249,0.01000,2.309
+2,mlp.up_proj,0.0001909173,0.01000,2.337
+2,mlp.down_proj,0.0000317416,0.01000,3.353
+3,self_attn.k_proj,0.0000031279,0.01000,4.404
+3,self_attn.q_proj,0.0000144715,0.01000,4.428
+3,self_attn.v_proj,0.0000016724,0.01000,4.424
+3,self_attn.o_proj,0.0000012538,0.01000,0.544
+3,mlp.gate_proj,0.0002528620,0.01000,2.388
+3,mlp.up_proj,0.0001356809,0.01000,2.385
+3,mlp.down_proj,0.0000074641,0.01000,3.344
+4,self_attn.q_proj,0.0000193357,0.01000,4.472
+4,self_attn.k_proj,0.0000038883,0.01000,4.473
+4,self_attn.v_proj,0.0000024538,0.01000,4.480
+4,self_attn.o_proj,0.0000015982,0.01000,0.535
+4,mlp.up_proj,0.0001098662,0.01000,2.342
+4,mlp.gate_proj,0.0001805611,0.01000,2.356
+4,mlp.down_proj,0.0000093950,0.01000,3.289
+5,self_attn.k_proj,0.0000042987,0.01000,4.247
+5,self_attn.v_proj,0.0000030784,0.01000,4.288
+5,self_attn.q_proj,0.0000199220,0.01000,4.307
+5,self_attn.o_proj,0.0000023912,0.01000,0.551
+5,mlp.up_proj,0.0002314192,0.01000,2.304
+5,mlp.gate_proj,0.0003550911,0.01000,2.321
+5,mlp.down_proj,0.0000080654,0.01000,3.315
+6,self_attn.q_proj,0.0000258464,0.01000,4.283
+6,self_attn.v_proj,0.0000021261,0.01000,4.316
+6,self_attn.k_proj,0.0000056151,0.01000,4.332
+6,self_attn.o_proj,0.0000012407,0.01000,0.547
+6,mlp.up_proj,0.0000897951,0.01000,2.361
+6,mlp.gate_proj,0.0001075854,0.01000,2.372
+6,mlp.down_proj,0.0000088174,0.01000,3.313
+7,self_attn.q_proj,0.0000118383,0.01000,4.482
+7,self_attn.k_proj,0.0000024726,0.01000,4.512
+7,self_attn.v_proj,0.0000017876,0.01000,4.510
+7,self_attn.o_proj,0.0000017164,0.01000,0.546
+7,mlp.up_proj,0.0000836660,0.01000,2.344
+7,mlp.gate_proj,0.0000883657,0.01000,2.350
+7,mlp.down_proj,0.0000089362,0.01000,3.284
+8,self_attn.q_proj,0.0000253838,0.01000,4.277
+8,self_attn.v_proj,0.0000023319,0.01000,4.296
+8,self_attn.k_proj,0.0000044788,0.01000,4.316
+8,self_attn.o_proj,0.0000023788,0.01000,0.545
+8,mlp.gate_proj,0.0000882580,0.01000,2.339
+8,mlp.up_proj,0.0000811948,0.01000,2.352
+8,mlp.down_proj,0.0000082430,0.01000,3.307
+9,self_attn.k_proj,0.0000039779,0.01000,4.418
+9,self_attn.q_proj,0.0000186251,0.01000,4.423
+9,self_attn.v_proj,0.0000020524,0.01000,4.436
+9,self_attn.o_proj,0.0000020282,0.01000,0.542
+9,mlp.up_proj,0.0000763025,0.01000,2.345
+9,mlp.gate_proj,0.0000786601,0.01000,2.348
+9,mlp.down_proj,0.0000078499,0.01000,3.313
+10,self_attn.q_proj,0.0000200244,0.01000,4.472
+10,self_attn.v_proj,0.0000032090,0.01000,4.506
+10,self_attn.k_proj,0.0000039560,0.01000,4.510
+10,self_attn.o_proj,0.0000032987,0.01000,0.557
+10,mlp.up_proj,0.0000711971,0.01000,2.357
+10,mlp.gate_proj,0.0000751373,0.01000,2.365
+10,mlp.down_proj,0.0000069655,0.01000,3.306
+11,self_attn.q_proj,0.0000185073,0.01000,4.388
+11,self_attn.k_proj,0.0000036776,0.01000,4.405
+11,self_attn.v_proj,0.0000024440,0.01000,4.412
+11,self_attn.o_proj,0.0000030892,0.01000,0.535
+11,mlp.gate_proj,0.0000711098,0.01000,2.348
+11,mlp.up_proj,0.0000631271,0.01000,2.350
+11,mlp.down_proj,0.0000056081,0.01000,3.301
+12,self_attn.q_proj,0.0000228144,0.01000,4.349
+12,self_attn.v_proj,0.0000023832,0.01000,4.388
+12,self_attn.k_proj,0.0000048670,0.01000,4.388
+12,self_attn.o_proj,0.0000024755,0.01000,0.538
+12,mlp.gate_proj,0.0000657909,0.01000,2.302
+12,mlp.up_proj,0.0000612288,0.01000,2.311
+12,mlp.down_proj,0.0000059455,0.01000,3.302
+13,self_attn.v_proj,0.0000018356,0.01000,4.256
+13,self_attn.q_proj,0.0000138097,0.01000,4.262
+13,self_attn.k_proj,0.0000028020,0.01000,4.276
+13,self_attn.o_proj,0.0000028769,0.01000,0.536
+13,mlp.gate_proj,0.0000610501,0.01000,2.302
+13,mlp.up_proj,0.0000588356,0.01000,2.316
+13,mlp.down_proj,0.0000051917,0.01000,3.321
+14,self_attn.q_proj,0.0000314814,0.01000,4.263
+14,self_attn.k_proj,0.0000048088,0.01000,4.279
+14,self_attn.v_proj,0.0000032079,0.01000,4.287
+14,self_attn.o_proj,0.0000026274,0.01000,0.540
+14,mlp.up_proj,0.0000671807,0.01000,2.314
+14,mlp.gate_proj,0.0000653831,0.01000,2.328
+14,mlp.down_proj,0.0000063804,0.01000,3.282
+15,self_attn.q_proj,0.0000419127,0.01000,4.216
+15,self_attn.k_proj,0.0000035704,0.01000,4.277
+15,self_attn.v_proj,0.0000031669,0.01000,4.283
+15,self_attn.o_proj,0.0000037156,0.01000,0.547
+15,mlp.gate_proj,0.0000573770,0.01000,2.359
+15,mlp.up_proj,0.0000551630,0.01000,2.370
+15,mlp.down_proj,0.0000050383,0.01000,3.277
+16,self_attn.q_proj,0.0000248484,0.01000,4.308
+16,self_attn.k_proj,0.0000046485,0.01000,4.339
+16,self_attn.v_proj,0.0000034968,0.01000,4.347
+16,self_attn.o_proj,0.0000028846,0.01000,0.536
+16,mlp.up_proj,0.0000633835,0.01000,2.353
+16,mlp.gate_proj,0.0000640739,0.01000,2.372
+16,mlp.down_proj,0.0000059960,0.01000,3.295
+17,self_attn.v_proj,0.0000045602,0.01000,4.281
+17,self_attn.k_proj,0.0000027827,0.01000,4.304
+17,self_attn.q_proj,0.0000229154,0.01000,4.321
+17,self_attn.o_proj,0.0000026632,0.01000,0.541
+17,mlp.up_proj,0.0000619624,0.01000,2.263
+17,mlp.gate_proj,0.0000617136,0.01000,2.282
+17,mlp.down_proj,0.0000067396,0.01000,3.347
+18,self_attn.q_proj,0.0000180023,0.01000,4.310
+18,self_attn.v_proj,0.0000030239,0.01000,4.324
+18,self_attn.k_proj,0.0000030804,0.01000,4.343
+18,self_attn.o_proj,0.0000037993,0.01000,0.547
+18,mlp.gate_proj,0.0000655076,0.01000,2.243
+18,mlp.up_proj,0.0000648117,0.01000,2.263
+18,mlp.down_proj,0.0000085318,0.01000,3.360
+19,self_attn.k_proj,0.0000035608,0.01000,4.246
+19,self_attn.q_proj,0.0000249501,0.01000,4.262
+19,self_attn.v_proj,0.0000062126,0.01000,4.291
+19,self_attn.o_proj,0.0000036369,0.01000,0.544
+19,mlp.up_proj,0.0000767578,0.01000,2.335
+19,mlp.gate_proj,0.0000716194,0.01000,2.348
+19,mlp.down_proj,0.0000148985,0.01000,3.327
+20,self_attn.v_proj,0.0000082651,0.01000,4.172
+20,self_attn.q_proj,0.0000268460,0.01000,4.222
+20,self_attn.k_proj,0.0000041337,0.01000,4.239
+20,self_attn.o_proj,0.0000064470,0.01000,0.555
+20,mlp.up_proj,0.0000856933,0.01000,2.221
+20,mlp.gate_proj,0.0000835763,0.01000,2.231
+20,mlp.down_proj,0.0000151029,0.01000,3.344
+21,self_attn.k_proj,0.0000040809,0.01000,4.179
+21,self_attn.v_proj,0.0000075748,0.01000,4.201
+21,self_attn.q_proj,0.0000287211,0.01000,4.221
+21,self_attn.o_proj,0.0000043775,0.01000,0.541
+21,mlp.up_proj,0.0001197178,0.01000,2.279
+21,mlp.gate_proj,0.0001174506,0.01000,2.297
+21,mlp.down_proj,0.0000260825,0.01000,3.305
+22,self_attn.q_proj,0.0000269875,0.01000,4.200
+22,self_attn.v_proj,0.0000097490,0.01000,4.244
+22,self_attn.k_proj,0.0000047460,0.01000,4.259
+22,self_attn.o_proj,0.0000063245,0.01000,0.555
+22,mlp.gate_proj,0.0001409212,0.01000,2.244
+22,mlp.up_proj,0.0001417933,0.01000,2.262
+22,mlp.down_proj,0.0000369983,0.01000,3.340
+23,self_attn.q_proj,0.0000357684,0.01000,4.041
+23,self_attn.k_proj,0.0000055682,0.01000,4.054
+23,self_attn.v_proj,0.0000130947,0.01000,4.086
+23,self_attn.o_proj,0.0000059521,0.01000,0.553
+23,mlp.up_proj,0.0001628146,0.01000,2.163
+23,mlp.gate_proj,0.0001548556,0.01000,2.189
+23,mlp.down_proj,0.0000520813,0.01000,3.319
+24,self_attn.q_proj,0.0000388998,0.01000,4.205
+24,self_attn.v_proj,0.0000273622,0.01000,4.235
+24,self_attn.k_proj,0.0000063280,0.01000,4.245
+24,self_attn.o_proj,0.0000080088,0.01000,0.553
+24,mlp.up_proj,0.0001850207,0.01000,2.170
+24,mlp.gate_proj,0.0001719786,0.01000,2.176
+24,mlp.down_proj,0.0000647621,0.01000,3.320
+25,self_attn.k_proj,0.0000072995,0.01000,4.195
+25,self_attn.v_proj,0.0000450367,0.01000,4.221
+25,self_attn.q_proj,0.0000414084,0.01000,4.245
+25,self_attn.o_proj,0.0000182372,0.01000,0.540
+25,mlp.up_proj,0.0002051835,0.01000,2.191
+25,mlp.gate_proj,0.0001776770,0.01000,2.214
+25,mlp.down_proj,0.0000878944,0.01000,3.312
+26,self_attn.q_proj,0.0000454261,0.01000,4.018
+26,self_attn.v_proj,0.0000527841,0.01000,4.032
+26,self_attn.k_proj,0.0000070298,0.01000,4.067
+26,self_attn.o_proj,0.0000093331,0.01000,0.539
+26,mlp.gate_proj,0.0001749531,0.01000,2.183
+26,mlp.up_proj,0.0002100867,0.01000,2.201
+26,mlp.down_proj,0.0001301046,0.01000,3.305
+27,self_attn.k_proj,0.0000076731,0.01000,4.093
+27,self_attn.q_proj,0.0000476585,0.01000,4.125
+27,self_attn.v_proj,0.0000559430,0.01000,4.149
+27,self_attn.o_proj,0.0000353431,0.01000,0.541
+27,mlp.up_proj,0.0002494651,0.01000,2.068
+27,mlp.gate_proj,0.0002388708,0.01000,2.082
+27,mlp.down_proj,0.0001699130,0.01000,3.293

qwen25-1p5b__gptq__wikitext2__n128__s2/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_iz40g1x9",
+    "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__n128__s2/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n128__s2/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
+}