Upload folder using huggingface_hub

.gitattributes

@@ -52,3 +52,4 @@ qwen25-1p5b__awq__wikitext2__n32__s2/tokenizer.json filter=lfs diff=lfs merge=lf
 qwen25-1p5b__awq__wikitext2__n512__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__awq__wikitext2__n512__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__awq__wikitext2__n512__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__openhermes__n128__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n128__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T20:06:49.326166+00:00

qwen25-1p5b__gptq__openhermes__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__openhermes__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_v0zvczir",
+      "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__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__openhermes__n128__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccd276dd3df6982642312f5be945e3c57cd7ab4f685a185773a07ca5abf8cdc
+size 1149862904

qwen25-1p5b__gptq__openhermes__n128__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000005278,0.01000,1.957
+0,self_attn.k_proj,0.0000044686,0.01000,1.969
+0,self_attn.q_proj,0.0000324913,0.01000,1.970
+0,self_attn.o_proj,0.0000011873,0.01000,0.383
+0,mlp.gate_proj,0.0000135689,0.01000,1.064
+0,mlp.up_proj,0.0000092988,0.01000,1.069
+0,mlp.down_proj,0.0000020358,0.01000,2.435
+1,self_attn.q_proj,0.0000050148,0.01000,1.951
+1,self_attn.v_proj,0.0000003320,0.01000,1.960
+1,self_attn.k_proj,0.0000014859,0.01000,1.964
+1,self_attn.o_proj,0.0000004744,0.01000,0.374
+1,mlp.gate_proj,0.0003761280,0.01000,1.080
+1,mlp.up_proj,0.0003058618,0.01000,1.083
+1,mlp.down_proj,0.0000122649,0.01000,2.421
+2,self_attn.v_proj,0.0000013755,0.01000,1.915
+2,self_attn.q_proj,0.0000154167,0.01000,1.924
+2,self_attn.k_proj,0.0000033478,0.01000,1.933
+2,self_attn.o_proj,0.0000009585,0.01000,0.382
+2,mlp.gate_proj,0.0003298771,0.01000,1.015
+2,mlp.up_proj,0.0002048084,0.01000,1.018
+2,mlp.down_proj,0.0000297104,0.01000,2.423
+3,self_attn.k_proj,0.0000033699,0.01000,1.936
+3,self_attn.v_proj,0.0000017597,0.01000,1.937
+3,self_attn.q_proj,0.0000155651,0.01000,1.945
+3,self_attn.o_proj,0.0000013493,0.01000,0.377
+3,mlp.up_proj,0.0001420106,0.01000,1.006
+3,mlp.gate_proj,0.0002702530,0.01000,1.009
+3,mlp.down_proj,0.0000061346,0.01000,2.415
+4,self_attn.q_proj,0.0000203263,0.01000,2.183
+4,self_attn.k_proj,0.0000041073,0.01000,2.186
+4,self_attn.v_proj,0.0000025210,0.01000,2.195
+4,self_attn.o_proj,0.0000016326,0.01000,0.373
+4,mlp.gate_proj,0.0001887755,0.01000,1.102
+4,mlp.up_proj,0.0001123498,0.01000,1.108
+4,mlp.down_proj,0.0000075628,0.01000,2.428
+5,self_attn.q_proj,0.0000209472,0.01000,1.954
+5,self_attn.k_proj,0.0000045305,0.01000,1.965
+5,self_attn.v_proj,0.0000030807,0.01000,1.968
+5,self_attn.o_proj,0.0000023864,0.01000,0.378
+5,mlp.gate_proj,0.0003527966,0.01000,0.989
+5,mlp.up_proj,0.0002269452,0.01000,0.990
+5,mlp.down_proj,0.0000060722,0.01000,2.404
+6,self_attn.k_proj,0.0000057898,0.01000,2.185
+6,self_attn.q_proj,0.0000264034,0.01000,2.193
+6,self_attn.v_proj,0.0000020565,0.01000,2.202
+6,self_attn.o_proj,0.0000012448,0.01000,0.376
+6,mlp.gate_proj,0.0000998910,0.01000,1.087
+6,mlp.up_proj,0.0000821526,0.01000,1.091
+6,mlp.down_proj,0.0000074996,0.01000,2.407
+7,self_attn.k_proj,0.0000024425,0.01000,2.128
+7,self_attn.v_proj,0.0000017375,0.01000,2.132
+7,self_attn.q_proj,0.0000116628,0.01000,2.143
+7,self_attn.o_proj,0.0000016674,0.01000,0.374
+7,mlp.gate_proj,0.0000844856,0.01000,1.083
+7,mlp.up_proj,0.0000790734,0.01000,1.089
+7,mlp.down_proj,0.0000079870,0.01000,2.411
+8,self_attn.q_proj,0.0000258432,0.01000,1.880
+8,self_attn.v_proj,0.0000023212,0.01000,1.889
+8,self_attn.k_proj,0.0000045342,0.01000,1.893
+8,self_attn.o_proj,0.0000021407,0.01000,0.384
+8,mlp.up_proj,0.0000797760,0.01000,1.118
+8,mlp.gate_proj,0.0000875144,0.01000,1.123
+8,mlp.down_proj,0.0000074031,0.01000,2.427
+9,self_attn.q_proj,0.0000192425,0.01000,1.863
+9,self_attn.k_proj,0.0000041536,0.01000,1.864
+9,self_attn.v_proj,0.0000020865,0.01000,1.871
+9,self_attn.o_proj,0.0000020595,0.01000,0.379
+9,mlp.gate_proj,0.0000796140,0.01000,1.033
+9,mlp.up_proj,0.0000764742,0.01000,1.040
+9,mlp.down_proj,0.0000072789,0.01000,2.413
+10,self_attn.q_proj,0.0000210802,0.01000,2.082
+10,self_attn.k_proj,0.0000042298,0.01000,2.091
+10,self_attn.v_proj,0.0000033024,0.01000,2.093
+10,self_attn.o_proj,0.0000031674,0.01000,0.377
+10,mlp.up_proj,0.0000743676,0.01000,1.055
+10,mlp.gate_proj,0.0000789432,0.01000,1.061
+10,mlp.down_proj,0.0000069715,0.01000,2.412
+11,self_attn.q_proj,0.0000201303,0.01000,2.071
+11,self_attn.k_proj,0.0000040497,0.01000,2.078
+11,self_attn.v_proj,0.0000026525,0.01000,2.079
+11,self_attn.o_proj,0.0000028914,0.01000,0.377
+11,mlp.up_proj,0.0000669879,0.01000,1.070
+11,mlp.gate_proj,0.0000760869,0.01000,1.075
+11,mlp.down_proj,0.0000058208,0.01000,2.418
+12,self_attn.q_proj,0.0000245253,0.01000,1.970
+12,self_attn.k_proj,0.0000052629,0.01000,1.974
+12,self_attn.v_proj,0.0000025287,0.01000,1.978
+12,self_attn.o_proj,0.0000022509,0.01000,0.370
+12,mlp.up_proj,0.0000660161,0.01000,1.254
+12,mlp.gate_proj,0.0000715564,0.01000,1.259
+12,mlp.down_proj,0.0000062864,0.01000,2.400
+13,self_attn.k_proj,0.0000030323,0.01000,2.102
+13,self_attn.q_proj,0.0000149133,0.01000,2.106
+13,self_attn.v_proj,0.0000019901,0.01000,2.110
+13,self_attn.o_proj,0.0000023504,0.01000,0.375
+13,mlp.gate_proj,0.0000661131,0.01000,1.062
+13,mlp.up_proj,0.0000636757,0.01000,1.064
+13,mlp.down_proj,0.0000054271,0.01000,2.414
+14,self_attn.q_proj,0.0000344218,0.01000,1.979
+14,self_attn.k_proj,0.0000052667,0.01000,1.986
+14,self_attn.v_proj,0.0000035498,0.01000,1.990
+14,self_attn.o_proj,0.0000021564,0.01000,0.379
+14,mlp.gate_proj,0.0000703187,0.01000,1.056
+14,mlp.up_proj,0.0000721403,0.01000,1.067
+14,mlp.down_proj,0.0000064313,0.01000,2.416
+15,self_attn.q_proj,0.0000470239,0.01000,1.927
+15,self_attn.k_proj,0.0000038352,0.01000,1.928
+15,self_attn.v_proj,0.0000033398,0.01000,1.936
+15,self_attn.o_proj,0.0000035103,0.01000,0.379
+15,mlp.gate_proj,0.0000637054,0.01000,1.056
+15,mlp.up_proj,0.0000607402,0.01000,1.059
+15,mlp.down_proj,0.0000055772,0.01000,2.427
+16,self_attn.k_proj,0.0000050323,0.01000,1.849
+16,self_attn.q_proj,0.0000266884,0.01000,1.865
+16,self_attn.v_proj,0.0000037405,0.01000,1.865
+16,self_attn.o_proj,0.0000027664,0.01000,0.372
+16,mlp.up_proj,0.0000703869,0.01000,1.180
+16,mlp.gate_proj,0.0000720075,0.01000,1.187
+16,mlp.down_proj,0.0000071078,0.01000,2.404
+17,self_attn.k_proj,0.0000031663,0.01000,1.934
+17,self_attn.q_proj,0.0000260881,0.01000,1.946
+17,self_attn.v_proj,0.0000051152,0.01000,1.950
+17,self_attn.o_proj,0.0000026369,0.01000,0.376
+17,mlp.gate_proj,0.0000741475,0.01000,1.041
+17,mlp.up_proj,0.0000738593,0.01000,1.046
+17,mlp.down_proj,0.0000089555,0.01000,2.411
+18,self_attn.q_proj,0.0000217308,0.01000,2.021
+18,self_attn.v_proj,0.0000036829,0.01000,2.026
+18,self_attn.k_proj,0.0000037292,0.01000,2.030
+18,self_attn.o_proj,0.0000040292,0.01000,0.377
+18,mlp.up_proj,0.0000817134,0.01000,1.054
+18,mlp.gate_proj,0.0000825462,0.01000,1.061
+18,mlp.down_proj,0.0000119379,0.01000,2.425
+19,self_attn.v_proj,0.0000072734,0.01000,2.131
+19,self_attn.k_proj,0.0000043445,0.01000,2.135
+19,self_attn.q_proj,0.0000307797,0.01000,2.147
+19,self_attn.o_proj,0.0000047400,0.01000,0.379
+19,mlp.gate_proj,0.0000972800,0.01000,1.126
+19,mlp.up_proj,0.0001034490,0.01000,1.126
+19,mlp.down_proj,0.0000203980,0.01000,2.464
+20,self_attn.v_proj,0.0000099219,0.01000,2.056
+20,self_attn.q_proj,0.0000338532,0.01000,2.078
+20,self_attn.k_proj,0.0000051747,0.01000,2.094
+20,self_attn.o_proj,0.0000074419,0.01000,0.380
+20,mlp.up_proj,0.0001128830,0.01000,1.109
+20,mlp.gate_proj,0.0001103048,0.01000,1.114
+20,mlp.down_proj,0.0000212080,0.01000,2.498
+21,self_attn.q_proj,0.0000352026,0.01000,2.086
+21,self_attn.v_proj,0.0000091443,0.01000,2.096
+21,self_attn.k_proj,0.0000050062,0.01000,2.104
+21,self_attn.o_proj,0.0000049060,0.01000,0.383
+21,mlp.up_proj,0.0001589169,0.01000,1.250
+21,mlp.gate_proj,0.0001593032,0.01000,1.275
+21,mlp.down_proj,0.0000338768,0.01000,2.440
+22,self_attn.q_proj,0.0000328149,0.01000,1.897
+22,self_attn.v_proj,0.0000110396,0.01000,1.912
+22,self_attn.k_proj,0.0000057662,0.01000,1.914
+22,self_attn.o_proj,0.0000067689,0.01000,0.378
+22,mlp.up_proj,0.0001829750,0.01000,1.108
+22,mlp.gate_proj,0.0001855306,0.01000,1.116
+22,mlp.down_proj,0.0000436459,0.01000,2.422
+23,self_attn.q_proj,0.0000408355,0.01000,1.855
+23,self_attn.k_proj,0.0000063096,0.01000,1.863
+23,self_attn.v_proj,0.0000137931,0.01000,1.870
+23,self_attn.o_proj,0.0000074578,0.01000,0.376
+23,mlp.gate_proj,0.0001917525,0.01000,1.102
+23,mlp.up_proj,0.0001988921,0.01000,1.116
+23,mlp.down_proj,0.0000509837,0.01000,2.468
+24,self_attn.v_proj,0.0000276011,0.01000,2.063
+24,self_attn.k_proj,0.0000067883,0.01000,2.076
+24,self_attn.q_proj,0.0000419721,0.01000,2.088
+24,self_attn.o_proj,0.0000104693,0.01000,0.384
+24,mlp.up_proj,0.0002067963,0.01000,1.139
+24,mlp.gate_proj,0.0001920769,0.01000,1.146
+24,mlp.down_proj,0.0000597505,0.01000,2.486
+25,self_attn.k_proj,0.0000071583,0.01000,2.050
+25,self_attn.q_proj,0.0000404146,0.01000,2.071
+25,self_attn.v_proj,0.0000416047,0.01000,2.077
+25,self_attn.o_proj,0.0000125326,0.01000,0.396
+25,mlp.up_proj,0.0002198021,0.01000,1.172
+25,mlp.gate_proj,0.0001917363,0.01000,1.189
+25,mlp.down_proj,0.0000758136,0.01000,2.603
+26,self_attn.q_proj,0.0000474457,0.01000,2.235
+26,self_attn.k_proj,0.0000072644,0.01000,2.276
+26,self_attn.v_proj,0.0000526926,0.01000,2.288
+26,self_attn.o_proj,0.0000090227,0.01000,0.392
+26,mlp.up_proj,0.0002180098,0.01000,1.127
+26,mlp.gate_proj,0.0001831271,0.01000,1.175
+26,mlp.down_proj,0.0001106614,0.01000,2.533
+27,self_attn.v_proj,0.0000538816,0.01000,2.421
+27,self_attn.k_proj,0.0000074907,0.01000,2.424
+27,self_attn.q_proj,0.0000473844,0.01000,2.452
+27,self_attn.o_proj,0.0000304281,0.01000,0.400
+27,mlp.up_proj,0.0002521397,0.01000,1.113
+27,mlp.gate_proj,0.0002419958,0.01000,1.143
+27,mlp.down_proj,0.0001312504,0.01000,2.476

qwen25-1p5b__gptq__openhermes__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_v0zvczir",
+    "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__n128__s0/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__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
+}