Upload folder using huggingface_hub

.gitattributes

@@ -61,3 +61,4 @@ qwen25-1p5b__gptq__openhermes__n32__s2/tokenizer.json filter=lfs diff=lfs merge=
 qwen25-1p5b__gptq__openhermes__n512__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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__s1/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T18:44:08.587589+00:00

qwen25-1p5b__gptq__wikitext2__n128__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__n128__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_8psqm6oc",
+      "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__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__n128__s1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd73289e186eed83badb98bab6a55f76f148263a165a25c9caff879e2270fc0e
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n128__s1/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000005152,0.01000,4.079
+0,self_attn.q_proj,0.0000308275,0.01000,4.100
+0,self_attn.k_proj,0.0000043587,0.01000,4.098
+0,self_attn.o_proj,0.0000011869,0.01000,0.532
+0,mlp.gate_proj,0.0000133280,0.01000,2.265
+0,mlp.up_proj,0.0000091348,0.01000,2.282
+0,mlp.down_proj,0.0000021055,0.01000,3.267
+1,self_attn.v_proj,0.0000003189,0.01000,4.065
+1,self_attn.k_proj,0.0000014307,0.01000,4.086
+1,self_attn.q_proj,0.0000047843,0.01000,4.112
+1,self_attn.o_proj,0.0000004515,0.01000,0.538
+1,mlp.up_proj,0.0002898887,0.01000,2.240
+1,mlp.gate_proj,0.0003559066,0.01000,2.262
+1,mlp.down_proj,0.0000123418,0.01000,3.259
+2,self_attn.v_proj,0.0000013085,0.01000,4.271
+2,self_attn.q_proj,0.0000145617,0.01000,4.300
+2,self_attn.k_proj,0.0000031972,0.01000,4.313
+2,self_attn.o_proj,0.0000008528,0.01000,0.538
+2,mlp.up_proj,0.0001936950,0.01000,2.297
+2,mlp.gate_proj,0.0003095517,0.01000,2.313
+2,mlp.down_proj,0.0000322625,0.01000,3.319
+3,self_attn.k_proj,0.0000031901,0.01000,4.378
+3,self_attn.q_proj,0.0000147464,0.01000,4.409
+3,self_attn.v_proj,0.0000017004,0.01000,4.425
+3,self_attn.o_proj,0.0000012101,0.01000,0.532
+3,mlp.gate_proj,0.0002567468,0.01000,2.318
+3,mlp.up_proj,0.0001377092,0.01000,2.323
+3,mlp.down_proj,0.0000075195,0.01000,3.296
+4,self_attn.k_proj,0.0000039464,0.01000,4.244
+4,self_attn.q_proj,0.0000195602,0.01000,4.264
+4,self_attn.v_proj,0.0000024864,0.01000,4.260
+4,self_attn.o_proj,0.0000016615,0.01000,0.541
+4,mlp.gate_proj,0.0001827571,0.01000,2.322
+4,mlp.up_proj,0.0001110808,0.01000,2.341
+4,mlp.down_proj,0.0000096144,0.01000,3.276
+5,self_attn.k_proj,0.0000043620,0.01000,4.243
+5,self_attn.v_proj,0.0000031246,0.01000,4.257
+5,self_attn.q_proj,0.0000202572,0.01000,4.276
+5,self_attn.o_proj,0.0000023961,0.01000,0.542
+5,mlp.up_proj,0.0002333927,0.01000,2.288
+5,mlp.gate_proj,0.0003581055,0.01000,2.303
+5,mlp.down_proj,0.0000080857,0.01000,3.291
+6,self_attn.v_proj,0.0000021456,0.01000,4.442
+6,self_attn.q_proj,0.0000262222,0.01000,4.450
+6,self_attn.k_proj,0.0000056964,0.01000,4.462
+6,self_attn.o_proj,0.0000012808,0.01000,0.545
+6,mlp.gate_proj,0.0001076043,0.01000,2.277
+6,mlp.up_proj,0.0000898211,0.01000,2.294
+6,mlp.down_proj,0.0000087541,0.01000,3.289
+7,self_attn.k_proj,0.0000024725,0.01000,4.203
+7,self_attn.q_proj,0.0000118606,0.01000,4.213
+7,self_attn.v_proj,0.0000017917,0.01000,4.236
+7,self_attn.o_proj,0.0000017347,0.01000,0.540
+7,mlp.up_proj,0.0000830096,0.01000,2.315
+7,mlp.gate_proj,0.0000879376,0.01000,2.323
+7,mlp.down_proj,0.0000088375,0.01000,3.287
+8,self_attn.v_proj,0.0000023182,0.01000,4.167
+8,self_attn.k_proj,0.0000044964,0.01000,4.183
+8,self_attn.q_proj,0.0000253917,0.01000,4.201
+8,self_attn.o_proj,0.0000023567,0.01000,0.546
+8,mlp.gate_proj,0.0000875659,0.01000,2.275
+8,mlp.up_proj,0.0000804767,0.01000,2.289
+8,mlp.down_proj,0.0000081173,0.01000,3.297
+9,self_attn.q_proj,0.0000184904,0.01000,4.261
+9,self_attn.v_proj,0.0000020272,0.01000,4.261
+9,self_attn.k_proj,0.0000039726,0.01000,4.270
+9,self_attn.o_proj,0.0000020542,0.01000,0.533
+9,mlp.up_proj,0.0000751028,0.01000,2.362
+9,mlp.gate_proj,0.0000776281,0.01000,2.377
+9,mlp.down_proj,0.0000075917,0.01000,3.299
+10,self_attn.v_proj,0.0000031405,0.01000,4.375
+10,self_attn.q_proj,0.0000197799,0.01000,4.401
+10,self_attn.k_proj,0.0000039256,0.01000,4.407
+10,self_attn.o_proj,0.0000032533,0.01000,0.542
+10,mlp.gate_proj,0.0000737045,0.01000,2.414
+10,mlp.up_proj,0.0000697164,0.01000,2.424
+10,mlp.down_proj,0.0000067181,0.01000,3.316
+11,self_attn.q_proj,0.0000183021,0.01000,4.540
+11,self_attn.v_proj,0.0000024268,0.01000,4.540
+11,self_attn.k_proj,0.0000036484,0.01000,4.545
+11,self_attn.o_proj,0.0000030072,0.01000,0.540
+11,mlp.gate_proj,0.0000699797,0.01000,2.367
+11,mlp.up_proj,0.0000621016,0.01000,2.385
+11,mlp.down_proj,0.0000054953,0.01000,3.323
+12,self_attn.q_proj,0.0000227317,0.01000,4.512
+12,self_attn.k_proj,0.0000048333,0.01000,4.523
+12,self_attn.v_proj,0.0000023661,0.01000,4.522
+12,self_attn.o_proj,0.0000025069,0.01000,0.538
+12,mlp.gate_proj,0.0000655887,0.01000,2.426
+12,mlp.up_proj,0.0000608651,0.01000,2.436
+12,mlp.down_proj,0.0000059076,0.01000,3.288
+13,self_attn.v_proj,0.0000018252,0.01000,4.464
+13,self_attn.k_proj,0.0000027885,0.01000,4.478
+13,self_attn.q_proj,0.0000137811,0.01000,4.485
+13,self_attn.o_proj,0.0000028912,0.01000,0.550
+13,mlp.up_proj,0.0000581567,0.01000,2.382
+13,mlp.gate_proj,0.0000604557,0.01000,2.406
+13,mlp.down_proj,0.0000051282,0.01000,3.308
+14,self_attn.q_proj,0.0000315287,0.01000,4.345
+14,self_attn.v_proj,0.0000032242,0.01000,4.370
+14,self_attn.k_proj,0.0000047899,0.01000,4.385
+14,self_attn.o_proj,0.0000026506,0.01000,0.545
+14,mlp.gate_proj,0.0000645721,0.01000,2.377
+14,mlp.up_proj,0.0000663892,0.01000,2.377
+14,mlp.down_proj,0.0000062612,0.01000,3.303
+15,self_attn.q_proj,0.0000420231,0.01000,4.358
+15,self_attn.k_proj,0.0000035794,0.01000,4.388
+15,self_attn.v_proj,0.0000031438,0.01000,4.384
+15,self_attn.o_proj,0.0000036527,0.01000,0.532
+15,mlp.gate_proj,0.0000567743,0.01000,2.312
+15,mlp.up_proj,0.0000545087,0.01000,2.325
+15,mlp.down_proj,0.0000049358,0.01000,3.321
+16,self_attn.k_proj,0.0000046190,0.01000,4.211
+16,self_attn.q_proj,0.0000246894,0.01000,4.216
+16,self_attn.v_proj,0.0000034651,0.01000,4.244
+16,self_attn.o_proj,0.0000028876,0.01000,0.540
+16,mlp.gate_proj,0.0000633646,0.01000,2.311
+16,mlp.up_proj,0.0000626315,0.01000,2.313
+16,mlp.down_proj,0.0000058780,0.01000,3.266
+17,self_attn.k_proj,0.0000027696,0.01000,4.245
+17,self_attn.v_proj,0.0000045279,0.01000,4.286
+17,self_attn.q_proj,0.0000227763,0.01000,4.303
+17,self_attn.o_proj,0.0000026914,0.01000,0.534
+17,mlp.up_proj,0.0000613919,0.01000,2.358
+17,mlp.gate_proj,0.0000612049,0.01000,2.367
+17,mlp.down_proj,0.0000066883,0.01000,3.308
+18,self_attn.v_proj,0.0000030184,0.01000,4.284
+18,self_attn.k_proj,0.0000030689,0.01000,4.332
+18,self_attn.q_proj,0.0000179004,0.01000,4.343
+18,self_attn.o_proj,0.0000037626,0.01000,0.536
+18,mlp.up_proj,0.0000643958,0.01000,2.270
+18,mlp.gate_proj,0.0000651507,0.01000,2.287
+18,mlp.down_proj,0.0000084498,0.01000,3.290
+19,self_attn.q_proj,0.0000248762,0.01000,4.434
+19,self_attn.v_proj,0.0000062282,0.01000,4.454
+19,self_attn.k_proj,0.0000035399,0.01000,4.461
+19,self_attn.o_proj,0.0000036093,0.01000,0.550
+19,mlp.up_proj,0.0000763953,0.01000,2.318
+19,mlp.gate_proj,0.0000713716,0.01000,2.337
+19,mlp.down_proj,0.0000147593,0.01000,3.296
+20,self_attn.q_proj,0.0000267754,0.01000,4.363
+20,self_attn.k_proj,0.0000041580,0.01000,4.384
+20,self_attn.v_proj,0.0000082637,0.01000,4.398
+20,self_attn.o_proj,0.0000062639,0.01000,0.535
+20,mlp.up_proj,0.0000849664,0.01000,2.360
+20,mlp.gate_proj,0.0000828571,0.01000,2.373
+20,mlp.down_proj,0.0000148440,0.01000,3.290
+21,self_attn.v_proj,0.0000075302,0.01000,4.314
+21,self_attn.q_proj,0.0000284474,0.01000,4.329
+21,self_attn.k_proj,0.0000040594,0.01000,4.341
+21,self_attn.o_proj,0.0000044782,0.01000,0.534
+21,mlp.gate_proj,0.0001161777,0.01000,2.380
+21,mlp.up_proj,0.0001182307,0.01000,2.384
+21,mlp.down_proj,0.0000255693,0.01000,3.306
+22,self_attn.v_proj,0.0000097436,0.01000,4.351
+22,self_attn.q_proj,0.0000268284,0.01000,4.389
+22,self_attn.k_proj,0.0000047294,0.01000,4.394
+22,self_attn.o_proj,0.0000062347,0.01000,0.542
+22,mlp.up_proj,0.0001396654,0.01000,2.376
+22,mlp.gate_proj,0.0001386982,0.01000,2.390
+22,mlp.down_proj,0.0000361337,0.01000,3.296
+23,self_attn.q_proj,0.0000355587,0.01000,4.381
+23,self_attn.k_proj,0.0000055457,0.01000,4.405
+23,self_attn.v_proj,0.0000131506,0.01000,4.412
+23,self_attn.o_proj,0.0000059369,0.01000,0.547
+23,mlp.up_proj,0.0001599940,0.01000,2.367
+23,mlp.gate_proj,0.0001522509,0.01000,2.385
+23,mlp.down_proj,0.0000505626,0.01000,3.283
+24,self_attn.q_proj,0.0000386957,0.01000,4.374
+24,self_attn.k_proj,0.0000063065,0.01000,4.395
+24,self_attn.v_proj,0.0000273574,0.01000,4.408
+24,self_attn.o_proj,0.0000080704,0.01000,0.541
+24,mlp.up_proj,0.0001823705,0.01000,2.361
+24,mlp.gate_proj,0.0001698603,0.01000,2.367
+24,mlp.down_proj,0.0000628367,0.01000,3.293
+25,self_attn.v_proj,0.0000454209,0.01000,4.628
+25,self_attn.k_proj,0.0000073399,0.01000,4.663
+25,self_attn.q_proj,0.0000413836,0.01000,4.683
+25,self_attn.o_proj,0.0000182031,0.01000,0.539
+25,mlp.up_proj,0.0002007127,0.01000,2.353
+25,mlp.gate_proj,0.0001739147,0.01000,2.368
+25,mlp.down_proj,0.0000843971,0.01000,3.286
+26,self_attn.q_proj,0.0000455971,0.01000,4.061
+26,self_attn.v_proj,0.0000535336,0.01000,4.076
+26,self_attn.k_proj,0.0000070703,0.01000,4.110
+26,self_attn.o_proj,0.0000094509,0.01000,0.533
+26,mlp.gate_proj,0.0001724148,0.01000,2.239
+26,mlp.up_proj,0.0002062105,0.01000,2.251
+26,mlp.down_proj,0.0001257237,0.01000,3.286
+27,self_attn.q_proj,0.0000480627,0.01000,4.085
+27,self_attn.k_proj,0.0000077254,0.01000,4.100
+27,self_attn.v_proj,0.0000566960,0.01000,4.126
+27,self_attn.o_proj,0.0000360983,0.01000,0.533
+27,mlp.up_proj,0.0002457121,0.01000,2.265
+27,mlp.gate_proj,0.0002361677,0.01000,2.282
+27,mlp.down_proj,0.0001678163,0.01000,3.279

qwen25-1p5b__gptq__wikitext2__n128__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_8psqm6oc",
+    "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__s1/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n128__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
+}