Upload folder using huggingface_hub

.gitattributes

@@ -66,3 +66,4 @@ qwen25-1p5b__gptq__wikitext2__n128__s2/tokenizer.json filter=lfs diff=lfs merge=
 qwen25-1p5b__gptq__wikitext2__n32__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T19:09:27.318479+00:00

qwen25-1p5b__gptq__wikitext2__n512__s0/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__s0/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_w2wiwa_x",
+      "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__s0/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__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87ca4195cd1f2e48fb6ec8367f774d689cbeae8c8550765e88b0752b9aec7dc
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n512__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000001272,0.01000,3.989
+0,self_attn.k_proj,0.0000010815,0.01000,4.030
+0,self_attn.q_proj,0.0000076344,0.01000,4.030
+0,self_attn.o_proj,0.0000002946,0.01000,0.547
+0,mlp.up_proj,0.0000022634,0.01000,2.192
+0,mlp.gate_proj,0.0000033025,0.01000,2.193
+0,mlp.down_proj,0.0000005370,0.01000,3.305
+1,self_attn.v_proj,0.0000000789,0.01000,4.079
+1,self_attn.k_proj,0.0000003524,0.01000,4.094
+1,self_attn.q_proj,0.0000011828,0.01000,4.131
+1,self_attn.o_proj,0.0000001131,0.01000,0.539
+1,mlp.up_proj,0.0000718576,0.01000,2.174
+1,mlp.gate_proj,0.0000881906,0.01000,2.192
+1,mlp.down_proj,0.0000031474,0.01000,3.292
+2,self_attn.q_proj,0.0000036245,0.01000,4.130
+2,self_attn.v_proj,0.0000003264,0.01000,4.173
+2,self_attn.k_proj,0.0000007918,0.01000,4.199
+2,self_attn.o_proj,0.0000002151,0.01000,0.549
+2,mlp.gate_proj,0.0000768213,0.01000,2.238
+2,mlp.up_proj,0.0000481170,0.01000,2.252
+2,mlp.down_proj,0.0000066660,0.01000,3.312
+3,self_attn.k_proj,0.0000007951,0.01000,4.312
+3,self_attn.q_proj,0.0000036700,0.01000,4.343
+3,self_attn.v_proj,0.0000004250,0.01000,4.367
+3,self_attn.o_proj,0.0000003105,0.01000,0.552
+3,mlp.up_proj,0.0000343232,0.01000,2.173
+3,mlp.gate_proj,0.0000641425,0.01000,2.187
+3,mlp.down_proj,0.0000019663,0.01000,3.369
+4,self_attn.v_proj,0.0000006193,0.01000,4.237
+4,self_attn.q_proj,0.0000048855,0.01000,4.267
+4,self_attn.k_proj,0.0000009843,0.01000,4.274
+4,self_attn.o_proj,0.0000004305,0.01000,0.549
+4,mlp.up_proj,0.0000277065,0.01000,2.240
+4,mlp.gate_proj,0.0000455615,0.01000,2.265
+4,mlp.down_proj,0.0000025023,0.01000,3.362
+5,self_attn.k_proj,0.0000010942,0.01000,4.115
+5,self_attn.v_proj,0.0000007814,0.01000,4.150
+5,self_attn.q_proj,0.0000050587,0.01000,4.163
+5,self_attn.o_proj,0.0000006090,0.01000,0.546
+5,mlp.up_proj,0.0000584863,0.01000,2.367
+5,mlp.gate_proj,0.0000897836,0.01000,2.371
+5,mlp.down_proj,0.0000021273,0.01000,3.354
+6,self_attn.q_proj,0.0000065766,0.01000,3.932
+6,self_attn.v_proj,0.0000005397,0.01000,3.970
+6,self_attn.k_proj,0.0000014319,0.01000,3.990
+6,self_attn.o_proj,0.0000003242,0.01000,0.546
+6,mlp.gate_proj,0.0000272239,0.01000,2.027
+6,mlp.up_proj,0.0000227060,0.01000,2.051
+6,mlp.down_proj,0.0000023103,0.01000,3.303
+7,self_attn.k_proj,0.0000006292,0.01000,3.867
+7,self_attn.q_proj,0.0000030063,0.01000,3.890
+7,self_attn.v_proj,0.0000004539,0.01000,3.919
+7,self_attn.o_proj,0.0000004336,0.01000,0.538
+7,mlp.up_proj,0.0000211794,0.01000,2.086
+7,mlp.gate_proj,0.0000224219,0.01000,2.103
+7,mlp.down_proj,0.0000023369,0.01000,3.297
+8,self_attn.q_proj,0.0000064466,0.01000,3.932
+8,self_attn.v_proj,0.0000005901,0.01000,3.936
+8,self_attn.k_proj,0.0000011386,0.01000,3.962
+8,self_attn.o_proj,0.0000006114,0.01000,0.545
+8,mlp.gate_proj,0.0000222755,0.01000,2.149
+8,mlp.up_proj,0.0000205008,0.01000,2.157
+8,mlp.down_proj,0.0000021529,0.01000,3.253
+9,self_attn.k_proj,0.0000010093,0.01000,3.765
+9,self_attn.v_proj,0.0000005183,0.01000,3.783
+9,self_attn.q_proj,0.0000047171,0.01000,3.817
+9,self_attn.o_proj,0.0000005201,0.01000,0.539
+9,mlp.up_proj,0.0000192128,0.01000,2.072
+9,mlp.gate_proj,0.0000198379,0.01000,2.092
+9,mlp.down_proj,0.0000020157,0.01000,3.263
+10,self_attn.q_proj,0.0000050587,0.01000,4.066
+10,self_attn.v_proj,0.0000008029,0.01000,4.085
+10,self_attn.k_proj,0.0000009985,0.01000,4.118
+10,self_attn.o_proj,0.0000008393,0.01000,0.544
+10,mlp.gate_proj,0.0000189391,0.01000,2.159
+10,mlp.up_proj,0.0000179393,0.01000,2.175
+10,mlp.down_proj,0.0000017862,0.01000,3.304
+11,self_attn.k_proj,0.0000009333,0.01000,3.929
+11,self_attn.q_proj,0.0000046809,0.01000,3.961
+11,self_attn.v_proj,0.0000006185,0.01000,3.983
+11,self_attn.o_proj,0.0000007824,0.01000,0.542
+11,mlp.gate_proj,0.0000179151,0.01000,2.011
+11,mlp.up_proj,0.0000158885,0.01000,2.012
+11,mlp.down_proj,0.0000014542,0.01000,3.291
+12,self_attn.q_proj,0.0000057844,0.01000,4.067
+12,self_attn.v_proj,0.0000006004,0.01000,4.078
+12,self_attn.k_proj,0.0000012317,0.01000,4.093
+12,self_attn.o_proj,0.0000006439,0.01000,0.537
+12,mlp.up_proj,0.0000153956,0.01000,2.167
+12,mlp.gate_proj,0.0000165507,0.01000,2.184
+12,mlp.down_proj,0.0000015221,0.01000,3.302
+13,self_attn.v_proj,0.0000004613,0.01000,4.063
+13,self_attn.k_proj,0.0000007029,0.01000,4.085
+13,self_attn.q_proj,0.0000034679,0.01000,4.120
+13,self_attn.o_proj,0.0000007312,0.01000,0.539
+13,mlp.up_proj,0.0000147119,0.01000,2.039
+13,mlp.gate_proj,0.0000152733,0.01000,2.060
+13,mlp.down_proj,0.0000013222,0.01000,3.308
+14,self_attn.q_proj,0.0000079364,0.01000,3.956
+14,self_attn.v_proj,0.0000008057,0.01000,3.993
+14,self_attn.k_proj,0.0000012070,0.01000,4.018
+14,self_attn.o_proj,0.0000006814,0.01000,0.539
+14,mlp.gate_proj,0.0000163372,0.01000,2.182
+14,mlp.up_proj,0.0000167822,0.01000,2.194
+14,mlp.down_proj,0.0000016158,0.01000,3.308
+15,self_attn.k_proj,0.0000008962,0.01000,3.915
+15,self_attn.q_proj,0.0000106373,0.01000,3.946
+15,self_attn.v_proj,0.0000007927,0.01000,3.977
+15,self_attn.o_proj,0.0000009254,0.01000,0.551
+15,mlp.up_proj,0.0000137522,0.01000,2.153
+15,mlp.gate_proj,0.0000143460,0.01000,2.166
+15,mlp.down_proj,0.0000012871,0.01000,3.308
+16,self_attn.q_proj,0.0000062335,0.01000,3.657
+16,self_attn.v_proj,0.0000008745,0.01000,3.702
+16,self_attn.k_proj,0.0000011693,0.01000,3.723
+16,self_attn.o_proj,0.0000007305,0.01000,0.539
+16,mlp.gate_proj,0.0000160598,0.01000,2.112
+16,mlp.up_proj,0.0000158524,0.01000,2.126
+16,mlp.down_proj,0.0000015308,0.01000,3.285
+17,self_attn.k_proj,0.0000007039,0.01000,3.992
+17,self_attn.v_proj,0.0000011453,0.01000,4.014
+17,self_attn.q_proj,0.0000057653,0.01000,4.043
+17,self_attn.o_proj,0.0000006811,0.01000,0.539
+17,mlp.up_proj,0.0000155102,0.01000,2.178
+17,mlp.gate_proj,0.0000154619,0.01000,2.197
+17,mlp.down_proj,0.0000017177,0.01000,3.315
+18,self_attn.q_proj,0.0000045186,0.01000,3.911
+18,self_attn.v_proj,0.0000007608,0.01000,3.930
+18,self_attn.k_proj,0.0000007757,0.01000,3.964
+18,self_attn.o_proj,0.0000009497,0.01000,0.536
+18,mlp.gate_proj,0.0000164451,0.01000,2.048
+18,mlp.up_proj,0.0000162225,0.01000,2.060
+18,mlp.down_proj,0.0000021789,0.01000,3.256
+19,self_attn.k_proj,0.0000008929,0.01000,4.089
+19,self_attn.q_proj,0.0000062639,0.01000,4.122
+19,self_attn.v_proj,0.0000015669,0.01000,4.156
+19,self_attn.o_proj,0.0000009140,0.01000,0.542
+19,mlp.gate_proj,0.0000180733,0.01000,2.211
+19,mlp.up_proj,0.0000193259,0.01000,2.227
+19,mlp.down_proj,0.0000038294,0.01000,3.292
+20,self_attn.v_proj,0.0000020885,0.01000,3.874
+20,self_attn.q_proj,0.0000067573,0.01000,3.889
+20,self_attn.k_proj,0.0000010518,0.01000,3.895
+20,self_attn.o_proj,0.0000016170,0.01000,0.539
+20,mlp.gate_proj,0.0000211241,0.01000,2.101
+20,mlp.up_proj,0.0000216224,0.01000,2.112
+20,mlp.down_proj,0.0000039224,0.01000,3.292
+21,self_attn.k_proj,0.0000010394,0.01000,3.971
+21,self_attn.v_proj,0.0000019186,0.01000,4.003
+21,self_attn.q_proj,0.0000072737,0.01000,4.034
+21,self_attn.o_proj,0.0000011303,0.01000,0.540
+21,mlp.up_proj,0.0000303373,0.01000,2.276
+21,mlp.gate_proj,0.0000298728,0.01000,2.291
+21,mlp.down_proj,0.0000068184,0.01000,3.296
+22,self_attn.q_proj,0.0000068818,0.01000,4.071
+22,self_attn.v_proj,0.0000024914,0.01000,4.117
+22,self_attn.k_proj,0.0000012079,0.01000,4.140
+22,self_attn.o_proj,0.0000016173,0.01000,0.556
+22,mlp.gate_proj,0.0000357949,0.01000,2.197
+22,mlp.up_proj,0.0000359676,0.01000,2.219
+22,mlp.down_proj,0.0000097453,0.01000,3.316
+23,self_attn.k_proj,0.0000014222,0.01000,3.961
+23,self_attn.q_proj,0.0000091424,0.01000,3.974
+23,self_attn.v_proj,0.0000033446,0.01000,4.011
+23,self_attn.o_proj,0.0000015222,0.01000,0.546
+23,mlp.up_proj,0.0000412226,0.01000,2.259
+23,mlp.gate_proj,0.0000392644,0.01000,2.266
+23,mlp.down_proj,0.0000139138,0.01000,3.295
+24,self_attn.q_proj,0.0000099276,0.01000,4.143
+24,self_attn.v_proj,0.0000069792,0.01000,4.145
+24,self_attn.k_proj,0.0000016226,0.01000,4.169
+24,self_attn.o_proj,0.0000020327,0.01000,0.537
+24,mlp.up_proj,0.0000472949,0.01000,2.239
+24,mlp.gate_proj,0.0000439540,0.01000,2.255
+24,mlp.down_proj,0.0000173756,0.01000,3.309
+25,self_attn.k_proj,0.0000018730,0.01000,4.356
+25,self_attn.v_proj,0.0000115226,0.01000,4.389
+25,self_attn.q_proj,0.0000106342,0.01000,4.417
+25,self_attn.o_proj,0.0000046987,0.01000,0.544
+25,mlp.up_proj,0.0000522371,0.01000,2.187
+25,mlp.gate_proj,0.0000453025,0.01000,2.204
+25,mlp.down_proj,0.0000233605,0.01000,3.283
+26,self_attn.q_proj,0.0000116414,0.01000,4.152
+26,self_attn.v_proj,0.0000135399,0.01000,4.187
+26,self_attn.k_proj,0.0000018033,0.01000,4.216
+26,self_attn.o_proj,0.0000025553,0.01000,0.544
+26,mlp.gate_proj,0.0000448625,0.01000,2.135
+26,mlp.up_proj,0.0000537578,0.01000,2.155
+26,mlp.down_proj,0.0000342447,0.01000,3.289
+27,self_attn.k_proj,0.0000019664,0.01000,3.982
+27,self_attn.q_proj,0.0000122309,0.01000,4.005
+27,self_attn.v_proj,0.0000143711,0.01000,4.036
+27,self_attn.o_proj,0.0000095344,0.01000,0.550
+27,mlp.gate_proj,0.0000611924,0.01000,2.201
+27,mlp.up_proj,0.0000637404,0.01000,2.210
+27,mlp.down_proj,0.0000455953,0.01000,3.323

qwen25-1p5b__gptq__wikitext2__n512__s0/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_w2wiwa_x",
+    "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__s0/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n512__s0/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
+}