Upload folder using huggingface_hub

.gitattributes

@@ -55,3 +55,4 @@ qwen25-1p5b__awq__wikitext2__n512__s2/tokenizer.json filter=lfs diff=lfs merge=l
 qwen25-1p5b__gptq__openhermes__n128__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__openhermes__n128__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__openhermes__n128__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__openhermes__n32__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n32__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T19:47:35.883273+00:00

qwen25-1p5b__gptq__openhermes__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__openhermes__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__61vewvg",
+      "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__openhermes__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__openhermes__n32__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92cff49a3a787995ba9dd9751171d1b99d35ada78de73656402e19feb0ff406
+size 1149862904

qwen25-1p5b__gptq__openhermes__n32__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000020834,0.01000,2.060
+0,self_attn.k_proj,0.0000176541,0.01000,2.098
+0,self_attn.q_proj,0.0001276330,0.01000,2.684
+0,self_attn.o_proj,0.0000047300,0.01000,0.361
+0,mlp.up_proj,0.0000370357,0.01000,1.075
+0,mlp.gate_proj,0.0000540409,0.01000,1.076
+0,mlp.down_proj,0.0000071419,0.01000,2.361
+1,self_attn.k_proj,0.0000059025,0.01000,2.556
+1,self_attn.q_proj,0.0000198304,0.01000,2.569
+1,self_attn.v_proj,0.0000013156,0.01000,2.573
+1,self_attn.o_proj,0.0000018447,0.01000,0.362
+1,mlp.gate_proj,0.0014893073,0.01000,1.101
+1,mlp.up_proj,0.0012117501,0.01000,1.108
+1,mlp.down_proj,0.0000489216,0.01000,2.326
+2,self_attn.k_proj,0.0000132288,0.01000,2.013
+2,self_attn.v_proj,0.0000054253,0.01000,2.022
+2,self_attn.q_proj,0.0000607698,0.01000,2.030
+2,self_attn.o_proj,0.0000037189,0.01000,0.357
+2,mlp.gate_proj,0.0013010863,0.01000,0.972
+2,mlp.up_proj,0.0008090108,0.01000,0.976
+2,mlp.down_proj,0.0001190941,0.01000,2.342
+3,self_attn.v_proj,0.0000069397,0.01000,2.307
+3,self_attn.q_proj,0.0000612554,0.01000,2.325
+3,self_attn.k_proj,0.0000132472,0.01000,2.342
+3,self_attn.o_proj,0.0000050829,0.01000,0.417
+3,mlp.gate_proj,0.0010632540,0.01000,1.086
+3,mlp.up_proj,0.0005604170,0.01000,1.086
+3,mlp.down_proj,0.0000204422,0.01000,2.406
+4,self_attn.k_proj,0.0000160793,0.01000,2.123
+4,self_attn.q_proj,0.0000797214,0.01000,2.139
+4,self_attn.v_proj,0.0000099129,0.01000,2.138
+4,self_attn.o_proj,0.0000061317,0.01000,0.372
+4,mlp.up_proj,0.0004416855,0.01000,1.024
+4,mlp.gate_proj,0.0007389767,0.01000,1.032
+4,mlp.down_proj,0.0000257749,0.01000,2.400
+5,self_attn.v_proj,0.0000120897,0.01000,1.940
+5,self_attn.q_proj,0.0000818509,0.01000,1.943
+5,self_attn.k_proj,0.0000176819,0.01000,1.948
+5,self_attn.o_proj,0.0000093754,0.01000,0.371
+5,mlp.gate_proj,0.0013717632,0.01000,1.051
+5,mlp.up_proj,0.0008845133,0.01000,1.055
+5,mlp.down_proj,0.0000200023,0.01000,2.399
+6,self_attn.k_proj,0.0000222980,0.01000,2.074
+6,self_attn.v_proj,0.0000079562,0.01000,2.083
+6,self_attn.q_proj,0.0001019688,0.01000,2.085
+6,self_attn.o_proj,0.0000046860,0.01000,0.369
+6,mlp.up_proj,0.0003195295,0.01000,0.993
+6,mlp.gate_proj,0.0003873956,0.01000,1.000
+6,mlp.down_proj,0.0000255939,0.01000,2.410
+7,self_attn.v_proj,0.0000067185,0.01000,1.974
+7,self_attn.k_proj,0.0000094263,0.01000,1.984
+7,self_attn.q_proj,0.0000450430,0.01000,1.983
+7,self_attn.o_proj,0.0000063096,0.01000,0.376
+7,mlp.up_proj,0.0003084687,0.01000,1.061
+7,mlp.gate_proj,0.0003288548,0.01000,1.069
+7,mlp.down_proj,0.0000280133,0.01000,2.395
+8,self_attn.k_proj,0.0000175547,0.01000,1.910
+8,self_attn.q_proj,0.0001005995,0.01000,1.913
+8,self_attn.v_proj,0.0000090524,0.01000,1.925
+8,self_attn.o_proj,0.0000082432,0.01000,0.378
+8,mlp.gate_proj,0.0003424078,0.01000,1.025
+8,mlp.up_proj,0.0003129040,0.01000,1.024
+8,mlp.down_proj,0.0000262705,0.01000,2.435
+9,self_attn.v_proj,0.0000081740,0.01000,1.976
+9,self_attn.k_proj,0.0000161603,0.01000,1.992
+9,self_attn.q_proj,0.0000750347,0.01000,2.000
+9,self_attn.o_proj,0.0000077320,0.01000,0.372
+9,mlp.gate_proj,0.0003128085,0.01000,1.085
+9,mlp.up_proj,0.0003010466,0.01000,1.090
+9,mlp.down_proj,0.0000261451,0.01000,2.397
+10,self_attn.q_proj,0.0000821740,0.01000,1.847
+10,self_attn.k_proj,0.0000165500,0.01000,1.891
+10,self_attn.v_proj,0.0000130357,0.01000,1.902
+10,self_attn.o_proj,0.0000120086,0.01000,0.378
+10,mlp.up_proj,0.0002915118,0.01000,1.057
+10,mlp.gate_proj,0.0003087381,0.01000,1.065
+10,mlp.down_proj,0.0000248115,0.01000,2.415
+11,self_attn.k_proj,0.0000156780,0.01000,1.953
+11,self_attn.v_proj,0.0000103703,0.01000,1.963
+11,self_attn.q_proj,0.0000780832,0.01000,1.973
+11,self_attn.o_proj,0.0000110246,0.01000,0.370
+11,mlp.up_proj,0.0002595717,0.01000,1.024
+11,mlp.gate_proj,0.0002949891,0.01000,1.025
+11,mlp.down_proj,0.0000204014,0.01000,2.566
+12,self_attn.v_proj,0.0000097997,0.01000,2.441
+12,self_attn.k_proj,0.0000202686,0.01000,2.534
+12,self_attn.q_proj,0.0000947941,0.01000,2.560
+12,self_attn.o_proj,0.0000084988,0.01000,0.383
+12,mlp.up_proj,0.0002568589,0.01000,1.188
+12,mlp.gate_proj,0.0002777640,0.01000,1.191
+12,mlp.down_proj,0.0000223483,0.01000,2.450
+13,self_attn.k_proj,0.0000119050,0.01000,2.123
+13,self_attn.v_proj,0.0000077215,0.01000,2.141
+13,self_attn.q_proj,0.0000580722,0.01000,2.147
+13,self_attn.o_proj,0.0000090184,0.01000,0.385
+13,mlp.up_proj,0.0002481807,0.01000,1.236
+13,mlp.gate_proj,0.0002574256,0.01000,1.247
+13,mlp.down_proj,0.0000194326,0.01000,2.481
+14,self_attn.k_proj,0.0000203928,0.01000,2.475
+14,self_attn.q_proj,0.0001335194,0.01000,2.487
+14,self_attn.v_proj,0.0000137005,0.01000,2.498
+14,self_attn.o_proj,0.0000082271,0.01000,0.367
+14,mlp.up_proj,0.0002811617,0.01000,1.163
+14,mlp.gate_proj,0.0002740660,0.01000,1.172
+14,mlp.down_proj,0.0000230261,0.01000,2.381
+15,self_attn.q_proj,0.0001809574,0.01000,2.012
+15,self_attn.k_proj,0.0000148189,0.01000,2.011
+15,self_attn.v_proj,0.0000129424,0.01000,2.014
+15,self_attn.o_proj,0.0000133767,0.01000,0.371
+15,mlp.gate_proj,0.0002440097,0.01000,1.066
+15,mlp.up_proj,0.0002331825,0.01000,1.067
+15,mlp.down_proj,0.0000193872,0.01000,2.416
+16,self_attn.q_proj,0.0001028245,0.01000,2.136
+16,self_attn.k_proj,0.0000194030,0.01000,2.150
+16,self_attn.v_proj,0.0000144218,0.01000,2.158
+16,self_attn.o_proj,0.0000101135,0.01000,0.375
+16,mlp.gate_proj,0.0002755708,0.01000,1.016
+16,mlp.up_proj,0.0002699093,0.01000,1.019
+16,mlp.down_proj,0.0000247917,0.01000,2.495
+17,self_attn.k_proj,0.0000120863,0.01000,2.099
+17,self_attn.q_proj,0.0000999787,0.01000,2.117
+17,self_attn.v_proj,0.0000197001,0.01000,2.118
+17,self_attn.o_proj,0.0000097061,0.01000,0.372
+17,mlp.gate_proj,0.0002843303,0.01000,1.039
+17,mlp.up_proj,0.0002841974,0.01000,1.044
+17,mlp.down_proj,0.0000317277,0.01000,2.391
+18,self_attn.q_proj,0.0000833432,0.01000,1.887
+18,self_attn.v_proj,0.0000141546,0.01000,1.898
+18,self_attn.k_proj,0.0000142513,0.01000,1.904
+18,self_attn.o_proj,0.0000154230,0.01000,0.371
+18,mlp.up_proj,0.0003153065,0.01000,1.124
+18,mlp.gate_proj,0.0003178762,0.01000,1.133
+18,mlp.down_proj,0.0000422229,0.01000,2.392
+19,self_attn.k_proj,0.0000167379,0.01000,1.866
+19,self_attn.v_proj,0.0000280943,0.01000,1.863
+19,self_attn.q_proj,0.0001188181,0.01000,1.884
+19,self_attn.o_proj,0.0000183452,0.01000,0.377
+19,mlp.up_proj,0.0004004333,0.01000,1.015
+19,mlp.gate_proj,0.0003760823,0.01000,1.017
+19,mlp.down_proj,0.0000726843,0.01000,2.391
+20,self_attn.k_proj,0.0000199490,0.01000,2.216
+20,self_attn.v_proj,0.0000383125,0.01000,2.231
+20,self_attn.q_proj,0.0001312840,0.01000,2.237
+20,self_attn.o_proj,0.0000286156,0.01000,0.376
+20,mlp.up_proj,0.0004348257,0.01000,1.104
+20,mlp.gate_proj,0.0004232714,0.01000,1.112
+20,mlp.down_proj,0.0000746108,0.01000,2.389
+21,self_attn.q_proj,0.0001355440,0.01000,1.887
+21,self_attn.k_proj,0.0000192428,0.01000,1.897
+21,self_attn.v_proj,0.0000351260,0.01000,1.897
+21,self_attn.o_proj,0.0000182280,0.01000,0.371
+21,mlp.gate_proj,0.0006129590,0.01000,1.068
+21,mlp.up_proj,0.0006137914,0.01000,1.068
+21,mlp.down_proj,0.0001197038,0.01000,2.389
+22,self_attn.v_proj,0.0000424657,0.01000,1.869
+22,self_attn.k_proj,0.0000219346,0.01000,1.872
+22,self_attn.q_proj,0.0001265007,0.01000,1.877
+22,self_attn.o_proj,0.0000256934,0.01000,0.368
+22,mlp.up_proj,0.0007074713,0.01000,1.114
+22,mlp.gate_proj,0.0007144916,0.01000,1.123
+22,mlp.down_proj,0.0001547436,0.01000,2.394
+23,self_attn.v_proj,0.0000532147,0.01000,2.035
+23,self_attn.q_proj,0.0001576166,0.01000,2.051
+23,self_attn.k_proj,0.0000242450,0.01000,2.054
+23,self_attn.o_proj,0.0000284315,0.01000,0.374
+23,mlp.up_proj,0.0007699123,0.01000,1.053
+23,mlp.gate_proj,0.0007395010,0.01000,1.057
+23,mlp.down_proj,0.0001709232,0.01000,2.388
+24,self_attn.k_proj,0.0000261033,0.01000,1.888
+24,self_attn.v_proj,0.0001065366,0.01000,1.892
+24,self_attn.q_proj,0.0001617301,0.01000,1.901
+24,self_attn.o_proj,0.0000387156,0.01000,0.369
+24,mlp.gate_proj,0.0007430573,0.01000,1.054
+24,mlp.up_proj,0.0008003731,0.01000,1.059
+24,mlp.down_proj,0.0002000452,0.01000,2.396
+25,self_attn.v_proj,0.0001627064,0.01000,1.903
+25,self_attn.k_proj,0.0000278878,0.01000,1.915
+25,self_attn.q_proj,0.0001578732,0.01000,1.915
+25,self_attn.o_proj,0.0000456240,0.01000,0.378
+25,mlp.up_proj,0.0008555091,0.01000,1.054
+25,mlp.gate_proj,0.0007450755,0.01000,1.062
+25,mlp.down_proj,0.0002553797,0.01000,2.421
+26,self_attn.k_proj,0.0000282830,0.01000,1.929
+26,self_attn.v_proj,0.0002085737,0.01000,1.938
+26,self_attn.q_proj,0.0001851321,0.01000,1.949
+26,self_attn.o_proj,0.0000302229,0.01000,0.384
+26,mlp.up_proj,0.0008509027,0.01000,1.155
+26,mlp.gate_proj,0.0007135598,0.01000,1.166
+26,mlp.down_proj,0.0004016290,0.01000,2.465
+27,self_attn.k_proj,0.0000291468,0.01000,2.051
+27,self_attn.q_proj,0.0001840187,0.01000,2.070
+27,self_attn.v_proj,0.0002103980,0.01000,2.084
+27,self_attn.o_proj,0.0001110255,0.01000,0.381
+27,mlp.gate_proj,0.0009392411,0.01000,1.108
+27,mlp.up_proj,0.0009807142,0.01000,1.128
+27,mlp.down_proj,0.0004393744,0.01000,2.458

qwen25-1p5b__gptq__openhermes__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__61vewvg",
+    "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__openhermes__n32__s0/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__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
+}