Upload folder using huggingface_hub

.gitattributes

@@ -68,3 +68,4 @@ qwen25-1p5b__gptq__wikitext2__n32__s1/tokenizer.json filter=lfs diff=lfs merge=l
 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__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__wikitext2__n512__s2/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T19:41:31.099251+00:00

qwen25-1p5b__gptq__wikitext2__n512__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__n512__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_gcsd6lfi",
+      "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__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__n512__s2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce5381721754e4a6e87ba82ffdef99851e243a844ebab488a4006c7b5dd7f74
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n512__s2/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000077383,0.01000,4.029
+0,self_attn.v_proj,0.0000001288,0.01000,4.042
+0,self_attn.k_proj,0.0000010901,0.01000,4.063
+0,self_attn.o_proj,0.0000002965,0.01000,0.533
+0,mlp.gate_proj,0.0000033195,0.01000,2.085
+0,mlp.up_proj,0.0000022780,0.01000,2.097
+0,mlp.down_proj,0.0000005443,0.01000,3.291
+1,self_attn.k_proj,0.0000003575,0.01000,4.189
+1,self_attn.v_proj,0.0000000799,0.01000,4.221
+1,self_attn.q_proj,0.0000011976,0.01000,4.237
+1,self_attn.o_proj,0.0000001141,0.01000,0.534
+1,mlp.up_proj,0.0000725166,0.01000,2.262
+1,mlp.gate_proj,0.0000890598,0.01000,2.279
+1,mlp.down_proj,0.0000031995,0.01000,3.303
+2,self_attn.q_proj,0.0000036610,0.01000,3.999
+2,self_attn.v_proj,0.0000003286,0.01000,4.049
+2,self_attn.k_proj,0.0000007989,0.01000,4.072
+2,self_attn.o_proj,0.0000002173,0.01000,0.536
+2,mlp.gate_proj,0.0000775894,0.01000,2.184
+2,mlp.up_proj,0.0000485700,0.01000,2.194
+2,mlp.down_proj,0.0000080455,0.01000,3.285
+3,self_attn.q_proj,0.0000037048,0.01000,4.209
+3,self_attn.k_proj,0.0000008014,0.01000,4.236
+3,self_attn.v_proj,0.0000004284,0.01000,4.255
+3,self_attn.o_proj,0.0000003091,0.01000,0.554
+3,mlp.gate_proj,0.0000648219,0.01000,2.267
+3,mlp.up_proj,0.0000347107,0.01000,2.285
+3,mlp.down_proj,0.0000019909,0.01000,3.330
+4,self_attn.v_proj,0.0000006267,0.01000,4.144
+4,self_attn.q_proj,0.0000049464,0.01000,4.162
+4,self_attn.k_proj,0.0000009951,0.01000,4.177
+4,self_attn.o_proj,0.0000004295,0.01000,0.540
+4,mlp.gate_proj,0.0000461052,0.01000,2.287
+4,mlp.up_proj,0.0000279992,0.01000,2.290
+4,mlp.down_proj,0.0000025328,0.01000,3.266
+5,self_attn.k_proj,0.0000010998,0.01000,3.981
+5,self_attn.v_proj,0.0000007892,0.01000,4.008
+5,self_attn.q_proj,0.0000051103,0.01000,4.026
+5,self_attn.o_proj,0.0000006231,0.01000,0.539
+5,mlp.up_proj,0.0000587618,0.01000,2.170
+5,mlp.gate_proj,0.0000902568,0.01000,2.195
+5,mlp.down_proj,0.0000021226,0.01000,3.294
+6,self_attn.q_proj,0.0000066457,0.01000,4.369
+6,self_attn.v_proj,0.0000005427,0.01000,4.430
+6,self_attn.k_proj,0.0000014446,0.01000,4.435
+6,self_attn.o_proj,0.0000003231,0.01000,0.536
+6,mlp.gate_proj,0.0000274011,0.01000,2.068
+6,mlp.up_proj,0.0000228213,0.01000,2.089
+6,mlp.down_proj,0.0000023182,0.01000,3.273
+7,self_attn.k_proj,0.0000006342,0.01000,3.814
+7,self_attn.q_proj,0.0000030308,0.01000,3.844
+7,self_attn.v_proj,0.0000004561,0.01000,3.874
+7,self_attn.o_proj,0.0000004336,0.01000,0.541
+7,mlp.up_proj,0.0000213224,0.01000,2.152
+7,mlp.gate_proj,0.0000225900,0.01000,2.160
+7,mlp.down_proj,0.0000023567,0.01000,3.263
+8,self_attn.v_proj,0.0000005975,0.01000,4.168
+8,self_attn.q_proj,0.0000065123,0.01000,4.183
+8,self_attn.k_proj,0.0000011494,0.01000,4.193
+8,self_attn.o_proj,0.0000006113,0.01000,0.546
+8,mlp.gate_proj,0.0000224671,0.01000,2.214
+8,mlp.up_proj,0.0000206533,0.01000,2.227
+8,mlp.down_proj,0.0000021699,0.01000,3.293
+9,self_attn.v_proj,0.0000005236,0.01000,3.983
+9,self_attn.k_proj,0.0000010193,0.01000,3.989
+9,self_attn.q_proj,0.0000047591,0.01000,4.018
+9,self_attn.o_proj,0.0000005276,0.01000,0.532
+9,mlp.up_proj,0.0000193804,0.01000,2.267
+9,mlp.gate_proj,0.0000199914,0.01000,2.285
+9,mlp.down_proj,0.0000020215,0.01000,3.307
+10,self_attn.q_proj,0.0000050923,0.01000,3.929
+10,self_attn.v_proj,0.0000008104,0.01000,3.953
+10,self_attn.k_proj,0.0000010085,0.01000,3.986
+10,self_attn.o_proj,0.0000008409,0.01000,0.535
+10,mlp.gate_proj,0.0000190149,0.01000,2.182
+10,mlp.up_proj,0.0000180016,0.01000,2.202
+10,mlp.down_proj,0.0000017744,0.01000,3.280
+11,self_attn.k_proj,0.0000009433,0.01000,3.864
+11,self_attn.q_proj,0.0000047038,0.01000,3.875
+11,self_attn.v_proj,0.0000006229,0.01000,3.919
+11,self_attn.o_proj,0.0000007756,0.01000,0.541
+11,mlp.gate_proj,0.0000180090,0.01000,2.167
+11,mlp.up_proj,0.0000159714,0.01000,2.180
+11,mlp.down_proj,0.0000014551,0.01000,3.293
+12,self_attn.q_proj,0.0000058119,0.01000,3.910
+12,self_attn.v_proj,0.0000006039,0.01000,3.930
+12,self_attn.k_proj,0.0000012408,0.01000,3.943
+12,self_attn.o_proj,0.0000006503,0.01000,0.531
+12,mlp.up_proj,0.0000154956,0.01000,2.257
+12,mlp.gate_proj,0.0000166721,0.01000,2.264
+12,mlp.down_proj,0.0000015331,0.01000,3.290
+13,self_attn.k_proj,0.0000007064,0.01000,4.080
+13,self_attn.v_proj,0.0000004640,0.01000,4.113
+13,self_attn.q_proj,0.0000034936,0.01000,4.129
+13,self_attn.o_proj,0.0000007339,0.01000,0.531
+13,mlp.up_proj,0.0000147718,0.01000,2.149
+13,mlp.gate_proj,0.0000153392,0.01000,2.167
+13,mlp.down_proj,0.0000013211,0.01000,3.288
+14,self_attn.q_proj,0.0000079671,0.01000,4.098
+14,self_attn.v_proj,0.0000008101,0.01000,4.135
+14,self_attn.k_proj,0.0000012150,0.01000,4.165
+14,self_attn.o_proj,0.0000006883,0.01000,0.539
+14,mlp.gate_proj,0.0000163706,0.01000,2.166
+14,mlp.up_proj,0.0000168279,0.01000,2.173
+14,mlp.down_proj,0.0000016180,0.01000,3.296
+15,self_attn.k_proj,0.0000009029,0.01000,4.312
+15,self_attn.q_proj,0.0000107412,0.01000,4.316
+15,self_attn.v_proj,0.0000007982,0.01000,4.345
+15,self_attn.o_proj,0.0000009356,0.01000,0.545
+15,mlp.up_proj,0.0000138340,0.01000,2.201
+15,mlp.gate_proj,0.0000144428,0.01000,2.201
+15,mlp.down_proj,0.0000012881,0.01000,3.278
+16,self_attn.v_proj,0.0000008809,0.01000,4.073
+16,self_attn.q_proj,0.0000062850,0.01000,4.112
+16,self_attn.k_proj,0.0000011770,0.01000,4.125
+16,self_attn.o_proj,0.0000007405,0.01000,0.539
+16,mlp.up_proj,0.0000159258,0.01000,2.123
+16,mlp.gate_proj,0.0000161285,0.01000,2.131
+16,mlp.down_proj,0.0000015308,0.01000,3.263
+17,self_attn.k_proj,0.0000007087,0.01000,4.057
+17,self_attn.v_proj,0.0000011495,0.01000,4.073
+17,self_attn.q_proj,0.0000058064,0.01000,4.100
+17,self_attn.o_proj,0.0000006971,0.01000,0.528
+17,mlp.up_proj,0.0000155857,0.01000,2.219
+17,mlp.gate_proj,0.0000155507,0.01000,2.235
+17,mlp.down_proj,0.0000017222,0.01000,3.290
+18,self_attn.q_proj,0.0000045429,0.01000,3.974
+18,self_attn.v_proj,0.0000007684,0.01000,4.032
+18,self_attn.k_proj,0.0000007845,0.01000,4.059
+18,self_attn.o_proj,0.0000009567,0.01000,0.548
+18,mlp.gate_proj,0.0000165117,0.01000,2.205
+18,mlp.up_proj,0.0000162928,0.01000,2.215
+18,mlp.down_proj,0.0000021836,0.01000,3.318
+19,self_attn.k_proj,0.0000008998,0.01000,3.923
+19,self_attn.q_proj,0.0000063016,0.01000,3.963
+19,self_attn.v_proj,0.0000015726,0.01000,3.978
+19,self_attn.o_proj,0.0000009222,0.01000,0.538
+19,mlp.up_proj,0.0000193820,0.01000,2.199
+19,mlp.gate_proj,0.0000181270,0.01000,2.217
+19,mlp.down_proj,0.0000038478,0.01000,3.260
+20,self_attn.q_proj,0.0000067969,0.01000,3.927
+20,self_attn.v_proj,0.0000021137,0.01000,3.942
+20,self_attn.k_proj,0.0000010543,0.01000,3.961
+20,self_attn.o_proj,0.0000016086,0.01000,0.532
+20,mlp.gate_proj,0.0000211343,0.01000,2.045
+20,mlp.up_proj,0.0000216527,0.01000,2.059
+20,mlp.down_proj,0.0000038913,0.01000,3.260
+21,self_attn.k_proj,0.0000010443,0.01000,3.877
+21,self_attn.v_proj,0.0000019202,0.01000,3.909
+21,self_attn.q_proj,0.0000072829,0.01000,3.935
+21,self_attn.o_proj,0.0000011263,0.01000,0.532
+21,mlp.up_proj,0.0000303155,0.01000,2.107
+21,mlp.gate_proj,0.0000298167,0.01000,2.133
+21,mlp.down_proj,0.0000068175,0.01000,3.297
+22,self_attn.q_proj,0.0000069020,0.01000,4.124
+22,self_attn.v_proj,0.0000024974,0.01000,4.173
+22,self_attn.k_proj,0.0000012147,0.01000,4.200
+22,self_attn.o_proj,0.0000016016,0.01000,0.548
+22,mlp.gate_proj,0.0000358783,0.01000,2.124
+22,mlp.up_proj,0.0000360159,0.01000,2.142
+22,mlp.down_proj,0.0000097558,0.01000,3.267
+23,self_attn.q_proj,0.0000091769,0.01000,4.106
+23,self_attn.k_proj,0.0000014285,0.01000,4.130
+23,self_attn.v_proj,0.0000033657,0.01000,4.157
+23,self_attn.o_proj,0.0000015382,0.01000,0.530
+23,mlp.up_proj,0.0000412258,0.01000,2.123
+23,mlp.gate_proj,0.0000393036,0.01000,2.137
+23,mlp.down_proj,0.0000138164,0.01000,3.294
+24,self_attn.v_proj,0.0000070122,0.01000,4.097
+24,self_attn.k_proj,0.0000016305,0.01000,4.119
+24,self_attn.q_proj,0.0000099470,0.01000,4.127
+24,self_attn.o_proj,0.0000021005,0.01000,0.534
+24,mlp.gate_proj,0.0000438400,0.01000,2.283
+24,mlp.up_proj,0.0000470848,0.01000,2.298
+24,mlp.down_proj,0.0000170960,0.01000,3.320
+25,self_attn.v_proj,0.0000115864,0.01000,4.101
+25,self_attn.k_proj,0.0000018835,0.01000,4.126
+25,self_attn.q_proj,0.0000106173,0.01000,4.148
+25,self_attn.o_proj,0.0000047906,0.01000,0.532
+25,mlp.gate_proj,0.0000449786,0.01000,2.256
+25,mlp.up_proj,0.0000518355,0.01000,2.276
+25,mlp.down_proj,0.0000230149,0.01000,3.315
+26,self_attn.q_proj,0.0000117110,0.01000,4.176
+26,self_attn.v_proj,0.0000136158,0.01000,4.210
+26,self_attn.k_proj,0.0000018123,0.01000,4.231
+26,self_attn.o_proj,0.0000025911,0.01000,0.554
+26,mlp.gate_proj,0.0000446334,0.01000,2.287
+26,mlp.up_proj,0.0000534109,0.01000,2.297
+26,mlp.down_proj,0.0000338740,0.01000,3.305
+27,self_attn.k_proj,0.0000019711,0.01000,4.213
+27,self_attn.q_proj,0.0000122932,0.01000,4.222
+27,self_attn.v_proj,0.0000144115,0.01000,4.254
+27,self_attn.o_proj,0.0000095650,0.01000,0.538
+27,mlp.up_proj,0.0000634301,0.01000,2.154
+27,mlp.gate_proj,0.0000609378,0.01000,2.169
+27,mlp.down_proj,0.0000453617,0.01000,3.287

qwen25-1p5b__gptq__wikitext2__n512__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_gcsd6lfi",
+    "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__s2/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n512__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
+}