Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__wikitext2__n128__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__wikitext2__n128__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T18:34:52.012267+00:00

qwen25-1p5b__gptq__wikitext2__n128__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__n128__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_a3xw7k9g",
+      "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__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__n128__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3195eef842b327b55dc158684833312a88f82ec00881543b76bf0847e82b12b2
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n128__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000005048,0.01000,4.197
+0,self_attn.q_proj,0.0000302414,0.01000,4.219
+0,self_attn.k_proj,0.0000042791,0.01000,4.237
+0,self_attn.o_proj,0.0000011696,0.01000,0.541
+0,mlp.up_proj,0.0000089902,0.01000,2.162
+0,mlp.gate_proj,0.0000130986,0.01000,2.170
+0,mlp.down_proj,0.0000020602,0.01000,3.269
+1,self_attn.v_proj,0.0000003135,0.01000,3.951
+1,self_attn.k_proj,0.0000014038,0.01000,3.976
+1,self_attn.q_proj,0.0000047105,0.01000,4.000
+1,self_attn.o_proj,0.0000004493,0.01000,0.537
+1,mlp.up_proj,0.0002857425,0.01000,2.281
+1,mlp.gate_proj,0.0003506964,0.01000,2.298
+1,mlp.down_proj,0.0000121036,0.01000,3.287
+2,self_attn.q_proj,0.0000143989,0.01000,4.078
+2,self_attn.v_proj,0.0000012891,0.01000,4.095
+2,self_attn.k_proj,0.0000031456,0.01000,4.122
+2,self_attn.o_proj,0.0000008583,0.01000,0.538
+2,mlp.gate_proj,0.0003053018,0.01000,2.216
+2,mlp.up_proj,0.0001912828,0.01000,2.238
+2,mlp.down_proj,0.0000312745,0.01000,3.289
+3,self_attn.k_proj,0.0000031436,0.01000,3.972
+3,self_attn.q_proj,0.0000145189,0.01000,3.994
+3,self_attn.v_proj,0.0000016809,0.01000,4.016
+3,self_attn.o_proj,0.0000012219,0.01000,0.541
+3,mlp.gate_proj,0.0002536784,0.01000,2.182
+3,mlp.up_proj,0.0001361068,0.01000,2.203
+3,mlp.down_proj,0.0000074360,0.01000,3.277
+4,self_attn.v_proj,0.0000024572,0.01000,3.934
+4,self_attn.q_proj,0.0000193480,0.01000,3.964
+4,self_attn.k_proj,0.0000039088,0.01000,3.968
+4,self_attn.o_proj,0.0000016648,0.01000,0.541
+4,mlp.gate_proj,0.0001808272,0.01000,2.312
+4,mlp.up_proj,0.0001100733,0.01000,2.325
+4,mlp.down_proj,0.0000095498,0.01000,3.276
+5,self_attn.v_proj,0.0000030925,0.01000,3.974
+5,self_attn.k_proj,0.0000043079,0.01000,3.981
+5,self_attn.q_proj,0.0000200109,0.01000,4.009
+5,self_attn.o_proj,0.0000024274,0.01000,0.544
+5,mlp.up_proj,0.0002315631,0.01000,2.192
+5,mlp.gate_proj,0.0003557568,0.01000,2.207
+5,mlp.down_proj,0.0000080346,0.01000,3.295
+6,self_attn.q_proj,0.0000259538,0.01000,4.203
+6,self_attn.v_proj,0.0000021249,0.01000,4.218
+6,self_attn.k_proj,0.0000056403,0.01000,4.240
+6,self_attn.o_proj,0.0000012716,0.01000,0.539
+6,mlp.gate_proj,0.0001074975,0.01000,2.315
+6,mlp.up_proj,0.0000896866,0.01000,2.327
+6,mlp.down_proj,0.0000088057,0.01000,3.317
+7,self_attn.k_proj,0.0000024730,0.01000,4.317
+7,self_attn.q_proj,0.0000118609,0.01000,4.343
+7,self_attn.v_proj,0.0000017796,0.01000,4.351
+7,self_attn.o_proj,0.0000016849,0.01000,0.542
+7,mlp.up_proj,0.0000838073,0.01000,2.254
+7,mlp.gate_proj,0.0000886841,0.01000,2.272
+7,mlp.down_proj,0.0000090611,0.01000,3.279
+8,self_attn.q_proj,0.0000254749,0.01000,4.092
+8,self_attn.v_proj,0.0000023462,0.01000,4.091
+8,self_attn.k_proj,0.0000044966,0.01000,4.117
+8,self_attn.o_proj,0.0000024067,0.01000,0.542
+8,mlp.gate_proj,0.0000885383,0.01000,2.271
+8,mlp.up_proj,0.0000814453,0.01000,2.280
+8,mlp.down_proj,0.0000083484,0.01000,3.279
+9,self_attn.k_proj,0.0000039825,0.01000,4.233
+9,self_attn.v_proj,0.0000020639,0.01000,4.262
+9,self_attn.q_proj,0.0000187050,0.01000,4.284
+9,self_attn.o_proj,0.0000020573,0.01000,0.531
+9,mlp.up_proj,0.0000764715,0.01000,2.247
+9,mlp.gate_proj,0.0000788467,0.01000,2.256
+9,mlp.down_proj,0.0000078403,0.01000,3.286
+10,self_attn.q_proj,0.0000200452,0.01000,3.983
+10,self_attn.v_proj,0.0000032104,0.01000,4.007
+10,self_attn.k_proj,0.0000039616,0.01000,4.034
+10,self_attn.o_proj,0.0000033142,0.01000,0.542
+10,mlp.gate_proj,0.0000750982,0.01000,2.223
+10,mlp.up_proj,0.0000712619,0.01000,2.236
+10,mlp.down_proj,0.0000069640,0.01000,3.289
+11,self_attn.k_proj,0.0000037042,0.01000,4.032
+11,self_attn.q_proj,0.0000184960,0.01000,4.048
+11,self_attn.v_proj,0.0000024469,0.01000,4.074
+11,self_attn.o_proj,0.0000030599,0.01000,0.543
+11,mlp.up_proj,0.0000631246,0.01000,2.238
+11,mlp.gate_proj,0.0000711062,0.01000,2.252
+11,mlp.down_proj,0.0000056197,0.01000,3.270
+12,self_attn.v_proj,0.0000023730,0.01000,3.925
+12,self_attn.q_proj,0.0000228401,0.01000,3.959
+12,self_attn.k_proj,0.0000048660,0.01000,3.963
+12,self_attn.o_proj,0.0000024677,0.01000,0.537
+12,mlp.gate_proj,0.0000658389,0.01000,2.225
+12,mlp.up_proj,0.0000612760,0.01000,2.237
+12,mlp.down_proj,0.0000059337,0.01000,3.291
+13,self_attn.k_proj,0.0000028074,0.01000,4.202
+13,self_attn.v_proj,0.0000018265,0.01000,4.232
+13,self_attn.q_proj,0.0000137718,0.01000,4.253
+13,self_attn.o_proj,0.0000028907,0.01000,0.546
+13,mlp.up_proj,0.0000586098,0.01000,2.258
+13,mlp.gate_proj,0.0000608662,0.01000,2.280
+13,mlp.down_proj,0.0000051772,0.01000,3.292
+14,self_attn.q_proj,0.0000314766,0.01000,4.183
+14,self_attn.v_proj,0.0000032024,0.01000,4.206
+14,self_attn.k_proj,0.0000047942,0.01000,4.230
+14,self_attn.o_proj,0.0000026679,0.01000,0.535
+14,mlp.gate_proj,0.0000649211,0.01000,2.306
+14,mlp.up_proj,0.0000665875,0.01000,2.317
+14,mlp.down_proj,0.0000062580,0.01000,3.298
+15,self_attn.k_proj,0.0000035639,0.01000,4.134
+15,self_attn.q_proj,0.0000418681,0.01000,4.174
+15,self_attn.v_proj,0.0000031223,0.01000,4.195
+15,self_attn.o_proj,0.0000036279,0.01000,0.542
+15,mlp.gate_proj,0.0000567642,0.01000,2.251
+15,mlp.up_proj,0.0000544475,0.01000,2.264
+15,mlp.down_proj,0.0000049219,0.01000,3.295
+16,self_attn.v_proj,0.0000034406,0.01000,4.238
+16,self_attn.q_proj,0.0000245993,0.01000,4.269
+16,self_attn.k_proj,0.0000045895,0.01000,4.277
+16,self_attn.o_proj,0.0000028234,0.01000,0.543
+16,mlp.gate_proj,0.0000633520,0.01000,2.370
+16,mlp.up_proj,0.0000625608,0.01000,2.384
+16,mlp.down_proj,0.0000058829,0.01000,3.300
+17,self_attn.k_proj,0.0000027661,0.01000,4.404
+17,self_attn.v_proj,0.0000045039,0.01000,4.436
+17,self_attn.q_proj,0.0000227042,0.01000,4.453
+17,self_attn.o_proj,0.0000026341,0.01000,0.539
+17,mlp.up_proj,0.0000614819,0.01000,2.333
+17,mlp.gate_proj,0.0000612637,0.01000,2.351
+17,mlp.down_proj,0.0000067094,0.01000,3.304
+18,self_attn.q_proj,0.0000178366,0.01000,4.302
+18,self_attn.v_proj,0.0000030099,0.01000,4.341
+18,self_attn.k_proj,0.0000030695,0.01000,4.360
+18,self_attn.o_proj,0.0000037842,0.01000,0.549
+18,mlp.gate_proj,0.0000649023,0.01000,2.304
+18,mlp.up_proj,0.0000642143,0.01000,2.322
+18,mlp.down_proj,0.0000084549,0.01000,3.319
+19,self_attn.q_proj,0.0000247891,0.01000,4.431
+19,self_attn.k_proj,0.0000035176,0.01000,4.452
+19,self_attn.v_proj,0.0000061693,0.01000,4.464
+19,self_attn.o_proj,0.0000035418,0.01000,0.545
+19,mlp.gate_proj,0.0000710459,0.01000,2.294
+19,mlp.up_proj,0.0000760288,0.01000,2.309
+19,mlp.down_proj,0.0000147377,0.01000,3.306
+20,self_attn.k_proj,0.0000040951,0.01000,4.313
+20,self_attn.q_proj,0.0000265484,0.01000,4.315
+20,self_attn.v_proj,0.0000082249,0.01000,4.324
+20,self_attn.o_proj,0.0000063014,0.01000,0.547
+20,mlp.gate_proj,0.0000828688,0.01000,2.334
+20,mlp.up_proj,0.0000848949,0.01000,2.340
+20,mlp.down_proj,0.0000148916,0.01000,3.292
+21,self_attn.v_proj,0.0000075221,0.01000,4.269
+21,self_attn.k_proj,0.0000040561,0.01000,4.302
+21,self_attn.q_proj,0.0000284343,0.01000,4.315
+21,self_attn.o_proj,0.0000043363,0.01000,0.538
+21,mlp.gate_proj,0.0001168702,0.01000,2.328
+21,mlp.up_proj,0.0001189386,0.01000,2.341
+21,mlp.down_proj,0.0000259512,0.01000,3.287
+22,self_attn.v_proj,0.0000097632,0.01000,4.242
+22,self_attn.q_proj,0.0000269040,0.01000,4.269
+22,self_attn.k_proj,0.0000047263,0.01000,4.272
+22,self_attn.o_proj,0.0000065070,0.01000,0.539
+22,mlp.gate_proj,0.0001393751,0.01000,2.401
+22,mlp.up_proj,0.0001401735,0.01000,2.414
+22,mlp.down_proj,0.0000366042,0.01000,3.298
+23,self_attn.q_proj,0.0000356564,0.01000,4.249
+23,self_attn.k_proj,0.0000055640,0.01000,4.269
+23,self_attn.v_proj,0.0000130584,0.01000,4.282
+23,self_attn.o_proj,0.0000059179,0.01000,0.536
+23,mlp.up_proj,0.0001613576,0.01000,2.339
+23,mlp.gate_proj,0.0001535601,0.01000,2.350
+23,mlp.down_proj,0.0000515026,0.01000,3.306
+24,self_attn.q_proj,0.0000388233,0.01000,4.145
+24,self_attn.k_proj,0.0000063121,0.01000,4.165
+24,self_attn.v_proj,0.0000271794,0.01000,4.172
+24,self_attn.o_proj,0.0000077751,0.01000,0.545
+24,mlp.up_proj,0.0001838824,0.01000,2.374
+24,mlp.gate_proj,0.0001709558,0.01000,2.375
+24,mlp.down_proj,0.0000637439,0.01000,3.284
+25,self_attn.k_proj,0.0000073203,0.01000,4.194
+25,self_attn.v_proj,0.0000451391,0.01000,4.209
+25,self_attn.q_proj,0.0000414386,0.01000,4.230
+25,self_attn.o_proj,0.0000181948,0.01000,0.536
+25,mlp.up_proj,0.0002035578,0.01000,2.238
+25,mlp.gate_proj,0.0001762586,0.01000,2.259
+25,mlp.down_proj,0.0000863165,0.01000,3.292
+26,self_attn.q_proj,0.0000455629,0.01000,4.062
+26,self_attn.v_proj,0.0000531516,0.01000,4.090
+26,self_attn.k_proj,0.0000070541,0.01000,4.119
+26,self_attn.o_proj,0.0000091481,0.01000,0.541
+26,mlp.gate_proj,0.0001737509,0.01000,2.254
+26,mlp.up_proj,0.0002083511,0.01000,2.267
+26,mlp.down_proj,0.0001279024,0.01000,3.300
+27,self_attn.k_proj,0.0000076360,0.01000,4.088
+27,self_attn.q_proj,0.0000476925,0.01000,4.122
+27,self_attn.v_proj,0.0000559478,0.01000,4.140
+27,self_attn.o_proj,0.0000342311,0.01000,0.552
+27,mlp.up_proj,0.0002477017,0.01000,2.311
+27,mlp.gate_proj,0.0002377383,0.01000,2.339
+27,mlp.down_proj,0.0001689918,0.01000,3.277

qwen25-1p5b__gptq__wikitext2__n128__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_a3xw7k9g",
+    "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__s0/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n128__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
+}