Upload folder using huggingface_hub

.gitattributes

@@ -63,3 +63,4 @@ qwen25-1p5b__gptq__openhermes__n512__s1/tokenizer.json filter=lfs diff=lfs merge
 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__n32__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__wikitext2__n32__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T18:09:18.277386+00:00

qwen25-1p5b__gptq__wikitext2__n32__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__n32__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_ju9ly8db",
+      "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__n32__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__n32__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6526201dbcc21834ec15be8418f00abc4ec60e985564553001de53225e9dba51
+size 1149862904

qwen25-1p5b__gptq__wikitext2__n32__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000019342,0.01000,3.674
+0,self_attn.k_proj,0.0000164271,0.01000,3.774
+0,self_attn.q_proj,0.0001147251,0.01000,4.146
+0,self_attn.o_proj,0.0000046329,0.01000,0.507
+0,mlp.up_proj,0.0000355683,0.01000,1.974
+0,mlp.gate_proj,0.0000519084,0.01000,1.992
+0,mlp.down_proj,0.0000071184,0.01000,3.188
+1,self_attn.v_proj,0.0000012361,0.01000,4.848
+1,self_attn.k_proj,0.0000055295,0.01000,4.853
+1,self_attn.q_proj,0.0000185897,0.01000,4.885
+1,self_attn.o_proj,0.0000017794,0.01000,0.511
+1,mlp.up_proj,0.0011307314,0.01000,2.749
+1,mlp.gate_proj,0.0013872794,0.01000,2.787
+1,mlp.down_proj,0.0000472508,0.01000,3.198
+2,self_attn.v_proj,0.0000050955,0.01000,3.837
+2,self_attn.q_proj,0.0000564199,0.01000,3.868
+2,self_attn.k_proj,0.0000123972,0.01000,3.891
+2,self_attn.o_proj,0.0000033651,0.01000,0.522
+2,mlp.gate_proj,0.0011960608,0.01000,2.260
+2,mlp.up_proj,0.0007519902,0.01000,2.281
+2,mlp.down_proj,0.0001024352,0.01000,3.203
+3,self_attn.q_proj,0.0000569727,0.01000,3.828
+3,self_attn.k_proj,0.0000123051,0.01000,3.830
+3,self_attn.v_proj,0.0000065804,0.01000,3.873
+3,self_attn.o_proj,0.0000047664,0.01000,0.524
+3,mlp.up_proj,0.0005349428,0.01000,2.058
+3,mlp.gate_proj,0.0009934762,0.01000,2.070
+3,mlp.down_proj,0.0000239868,0.01000,3.197
+4,self_attn.v_proj,0.0000096106,0.01000,3.840
+4,self_attn.k_proj,0.0000152209,0.01000,3.852
+4,self_attn.q_proj,0.0000755985,0.01000,3.873
+4,self_attn.o_proj,0.0000062767,0.01000,0.530
+4,mlp.gate_proj,0.0007045234,0.01000,2.143
+4,mlp.up_proj,0.0004306053,0.01000,2.148
+4,mlp.down_proj,0.0000318418,0.01000,3.179
+5,self_attn.v_proj,0.0000120225,0.01000,3.873
+5,self_attn.k_proj,0.0000166947,0.01000,3.902
+5,self_attn.q_proj,0.0000777669,0.01000,3.919
+5,self_attn.o_proj,0.0000093316,0.01000,0.523
+5,mlp.up_proj,0.0009004481,0.01000,2.103
+5,mlp.gate_proj,0.0013804892,0.01000,2.118
+5,mlp.down_proj,0.0000262128,0.01000,3.203
+6,self_attn.q_proj,0.0000997411,0.01000,3.978
+6,self_attn.v_proj,0.0000081930,0.01000,4.013
+6,self_attn.k_proj,0.0000215895,0.01000,4.030
+6,self_attn.o_proj,0.0000047831,0.01000,0.526
+6,mlp.gate_proj,0.0004120299,0.01000,2.135
+6,mlp.up_proj,0.0003444570,0.01000,2.154
+6,mlp.down_proj,0.0000296694,0.01000,3.201
+7,self_attn.k_proj,0.0000094747,0.01000,3.994
+7,self_attn.q_proj,0.0000453682,0.01000,4.025
+7,self_attn.v_proj,0.0000068652,0.01000,4.036
+7,self_attn.o_proj,0.0000064341,0.01000,0.534
+7,mlp.gate_proj,0.0003386944,0.01000,2.157
+7,mlp.up_proj,0.0003204946,0.01000,2.171
+7,mlp.down_proj,0.0000306689,0.01000,3.180
+8,self_attn.q_proj,0.0000975980,0.01000,4.055
+8,self_attn.k_proj,0.0000171185,0.01000,4.079
+8,self_attn.v_proj,0.0000089554,0.01000,4.082
+8,self_attn.o_proj,0.0000091898,0.01000,0.518
+8,mlp.up_proj,0.0003109178,0.01000,2.172
+8,mlp.gate_proj,0.0003373864,0.01000,2.194
+8,mlp.down_proj,0.0000282005,0.01000,3.202
+9,self_attn.k_proj,0.0000152093,0.01000,4.013
+9,self_attn.v_proj,0.0000078665,0.01000,4.037
+9,self_attn.q_proj,0.0000712139,0.01000,4.061
+9,self_attn.o_proj,0.0000077402,0.01000,0.526
+9,mlp.gate_proj,0.0003006670,0.01000,2.203
+9,mlp.up_proj,0.0002914813,0.01000,2.215
+9,mlp.down_proj,0.0000269406,0.01000,3.195
+10,self_attn.v_proj,0.0000122656,0.01000,4.445
+10,self_attn.q_proj,0.0000767830,0.01000,4.465
+10,self_attn.k_proj,0.0000151630,0.01000,4.466
+10,self_attn.o_proj,0.0000127585,0.01000,0.525
+10,mlp.gate_proj,0.0002860500,0.01000,2.161
+10,mlp.up_proj,0.0002715630,0.01000,2.170
+10,mlp.down_proj,0.0000238348,0.01000,3.218
+11,self_attn.k_proj,0.0000141979,0.01000,4.104
+11,self_attn.q_proj,0.0000709284,0.01000,4.131
+11,self_attn.v_proj,0.0000094011,0.01000,4.152
+11,self_attn.o_proj,0.0000115804,0.01000,0.515
+11,mlp.up_proj,0.0002399410,0.01000,2.111
+11,mlp.gate_proj,0.0002696267,0.01000,2.118
+11,mlp.down_proj,0.0000191793,0.01000,3.173
+12,self_attn.v_proj,0.0000091440,0.01000,4.016
+12,self_attn.k_proj,0.0000185371,0.01000,4.027
+12,self_attn.q_proj,0.0000872645,0.01000,4.041
+12,self_attn.o_proj,0.0000098156,0.01000,0.521
+12,mlp.up_proj,0.0002341574,0.01000,2.192
+12,mlp.gate_proj,0.0002522004,0.01000,2.201
+12,mlp.down_proj,0.0000209151,0.01000,3.217
+13,self_attn.v_proj,0.0000070881,0.01000,4.097
+13,self_attn.k_proj,0.0000108037,0.01000,4.116
+13,self_attn.q_proj,0.0000532102,0.01000,4.134
+13,self_attn.o_proj,0.0000111549,0.01000,0.528
+13,mlp.gate_proj,0.0002333046,0.01000,2.268
+13,mlp.up_proj,0.0002246042,0.01000,2.270
+13,mlp.down_proj,0.0000183048,0.01000,3.223
+14,self_attn.q_proj,0.0001213649,0.01000,4.056
+14,self_attn.v_proj,0.0000124703,0.01000,4.070
+14,self_attn.k_proj,0.0000184719,0.01000,4.092
+14,self_attn.o_proj,0.0000104451,0.01000,0.525
+14,mlp.gate_proj,0.0002496725,0.01000,2.223
+14,mlp.up_proj,0.0002567085,0.01000,2.239
+14,mlp.down_proj,0.0000224990,0.01000,3.217
+15,self_attn.v_proj,0.0000121300,0.01000,4.285
+15,self_attn.q_proj,0.0001598735,0.01000,4.316
+15,self_attn.k_proj,0.0000138054,0.01000,4.313
+15,self_attn.o_proj,0.0000142134,0.01000,0.519
+15,mlp.up_proj,0.0002091968,0.01000,2.164
+15,mlp.gate_proj,0.0002175755,0.01000,2.180
+15,mlp.down_proj,0.0000174174,0.01000,3.177
+16,self_attn.v_proj,0.0000133343,0.01000,4.080
+16,self_attn.q_proj,0.0000948552,0.01000,4.112
+16,self_attn.k_proj,0.0000176523,0.01000,4.121
+16,self_attn.o_proj,0.0000107418,0.01000,0.514
+16,mlp.gate_proj,0.0002441193,0.01000,2.216
+16,mlp.up_proj,0.0002420020,0.01000,2.232
+16,mlp.down_proj,0.0000209046,0.01000,3.202
+17,self_attn.k_proj,0.0000106545,0.01000,4.721
+17,self_attn.v_proj,0.0000174375,0.01000,4.770
+17,self_attn.q_proj,0.0000876165,0.01000,4.777
+17,self_attn.o_proj,0.0000100938,0.01000,0.557
+17,mlp.up_proj,0.0002374281,0.01000,2.085
+17,mlp.gate_proj,0.0002358815,0.01000,2.100
+17,mlp.down_proj,0.0000239344,0.01000,3.251
+18,self_attn.v_proj,0.0000115695,0.01000,3.946
+18,self_attn.q_proj,0.0000683989,0.01000,3.980
+18,self_attn.k_proj,0.0000117309,0.01000,3.990
+18,self_attn.o_proj,0.0000145658,0.01000,0.530
+18,mlp.gate_proj,0.0002511730,0.01000,2.065
+18,mlp.up_proj,0.0002487783,0.01000,2.079
+18,mlp.down_proj,0.0000302643,0.01000,3.252
+19,self_attn.k_proj,0.0000136190,0.01000,3.718
+19,self_attn.q_proj,0.0000958817,0.01000,3.754
+19,self_attn.v_proj,0.0000240136,0.01000,3.775
+19,self_attn.o_proj,0.0000142048,0.01000,0.522
+19,mlp.up_proj,0.0002968083,0.01000,1.998
+19,mlp.gate_proj,0.0002764180,0.01000,2.014
+19,mlp.down_proj,0.0000528821,0.01000,3.195
+20,self_attn.k_proj,0.0000158426,0.01000,4.033
+20,self_attn.v_proj,0.0000319307,0.01000,4.059
+20,self_attn.q_proj,0.0001033415,0.01000,4.065
+20,self_attn.o_proj,0.0000233880,0.01000,0.527
+20,mlp.gate_proj,0.0003184055,0.01000,2.033
+20,mlp.up_proj,0.0003276202,0.01000,2.044
+20,mlp.down_proj,0.0000513446,0.01000,3.257
+21,self_attn.k_proj,0.0000153072,0.01000,4.252
+21,self_attn.v_proj,0.0000287305,0.01000,4.271
+21,self_attn.q_proj,0.0001082291,0.01000,4.298
+21,self_attn.o_proj,0.0000156118,0.01000,0.525
+21,mlp.up_proj,0.0004525308,0.01000,2.103
+21,mlp.gate_proj,0.0004433999,0.01000,2.110
+21,mlp.down_proj,0.0000885168,0.01000,3.236
+22,self_attn.q_proj,0.0001016993,0.01000,4.133
+22,self_attn.v_proj,0.0000368748,0.01000,4.150
+22,self_attn.k_proj,0.0000178028,0.01000,4.178
+22,self_attn.o_proj,0.0000237580,0.01000,0.527
+22,mlp.gate_proj,0.0005231457,0.01000,2.072
+22,mlp.up_proj,0.0005282286,0.01000,2.103
+22,mlp.down_proj,0.0001215818,0.01000,3.211
+23,self_attn.q_proj,0.0001335094,0.01000,4.344
+23,self_attn.k_proj,0.0000207278,0.01000,4.366
+23,self_attn.v_proj,0.0000498450,0.01000,4.381
+23,self_attn.o_proj,0.0000223149,0.01000,0.537
+23,mlp.gate_proj,0.0005702716,0.01000,2.197
+23,mlp.up_proj,0.0006009719,0.01000,2.212
+23,mlp.down_proj,0.0001567543,0.01000,3.218
+24,self_attn.v_proj,0.0001028863,0.01000,4.407
+24,self_attn.q_proj,0.0001446288,0.01000,4.426
+24,self_attn.k_proj,0.0000236073,0.01000,4.422
+24,self_attn.o_proj,0.0000294283,0.01000,0.532
+24,mlp.gate_proj,0.0006296801,0.01000,2.155
+24,mlp.up_proj,0.0006763355,0.01000,2.175
+24,mlp.down_proj,0.0001902210,0.01000,3.234
+25,self_attn.v_proj,0.0001720013,0.01000,3.921
+25,self_attn.k_proj,0.0000277073,0.01000,3.939
+25,self_attn.q_proj,0.0001559415,0.01000,3.958
+25,self_attn.o_proj,0.0000675173,0.01000,0.523
+25,mlp.up_proj,0.0007389511,0.01000,2.089
+25,mlp.gate_proj,0.0006392358,0.01000,2.108
+25,mlp.down_proj,0.0002571768,0.01000,3.190
+26,self_attn.q_proj,0.0001713704,0.01000,3.633
+26,self_attn.v_proj,0.0002023745,0.01000,3.644
+26,self_attn.k_proj,0.0000266073,0.01000,3.682
+26,self_attn.o_proj,0.0000304375,0.01000,0.521
+26,mlp.gate_proj,0.0006336162,0.01000,1.928
+26,mlp.up_proj,0.0007597964,0.01000,1.947
+26,mlp.down_proj,0.0004217229,0.01000,3.178
+27,self_attn.k_proj,0.0000286929,0.01000,3.605
+27,self_attn.q_proj,0.0001791518,0.01000,3.645
+27,self_attn.v_proj,0.0002113884,0.01000,3.662
+27,self_attn.o_proj,0.0001239076,0.01000,0.526
+27,mlp.up_proj,0.0009051765,0.01000,1.981
+27,mlp.gate_proj,0.0008717191,0.01000,1.998
+27,mlp.down_proj,0.0005235551,0.01000,3.206

qwen25-1p5b__gptq__wikitext2__n32__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_ju9ly8db",
+    "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__n32__s0/tokenizer.json

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

qwen25-1p5b__gptq__wikitext2__n32__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
+}