Upload folder using huggingface_hub

.gitattributes

@@ -58,3 +58,4 @@ qwen25-1p5b__gptq__openhermes__n128__s2/tokenizer.json filter=lfs diff=lfs merge
 qwen25-1p5b__gptq__openhermes__n32__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__openhermes__n32__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen25-1p5b__gptq__openhermes__n32__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen25-1p5b__gptq__openhermes__n512__s0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n512__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T20:35:44.295175+00:00

qwen25-1p5b__gptq__openhermes__n512__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__n512__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_mn8so5j0",
+      "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__n512__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__n512__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae06e864dcbe15efb56d16d36e56b28a2bd06095ef82d6549828623f18074ce
+size 1149862904

qwen25-1p5b__gptq__openhermes__n512__s0/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000001364,0.01000,1.972
+0,self_attn.q_proj,0.0000084153,0.01000,1.978
+0,self_attn.k_proj,0.0000011566,0.01000,1.984
+0,self_attn.o_proj,0.0000002994,0.01000,0.383
+0,mlp.gate_proj,0.0000034130,0.01000,1.063
+0,mlp.up_proj,0.0000023364,0.01000,1.065
+0,mlp.down_proj,0.0000005354,0.01000,2.458
+1,self_attn.q_proj,0.0000012675,0.01000,2.070
+1,self_attn.v_proj,0.0000000841,0.01000,2.069
+1,self_attn.k_proj,0.0000003771,0.01000,2.078
+1,self_attn.o_proj,0.0000001202,0.01000,0.383
+1,mlp.up_proj,0.0000772533,0.01000,1.048
+1,mlp.gate_proj,0.0000951448,0.01000,1.051
+1,mlp.down_proj,0.0000031974,0.01000,2.431
+2,self_attn.v_proj,0.0000003490,0.01000,2.020
+2,self_attn.k_proj,0.0000008507,0.01000,2.036
+2,self_attn.q_proj,0.0000039183,0.01000,2.038
+2,self_attn.o_proj,0.0000002474,0.01000,0.381
+2,mlp.gate_proj,0.0000836867,0.01000,1.135
+2,mlp.up_proj,0.0000519041,0.01000,1.135
+2,mlp.down_proj,0.0000087973,0.01000,2.424
+3,self_attn.q_proj,0.0000039678,0.01000,1.924
+3,self_attn.k_proj,0.0000008601,0.01000,1.934
+3,self_attn.v_proj,0.0000004509,0.01000,1.938
+3,self_attn.o_proj,0.0000003487,0.01000,0.385
+3,mlp.up_proj,0.0000362302,0.01000,0.987
+3,mlp.gate_proj,0.0000691809,0.01000,0.995
+3,mlp.down_proj,0.0000016242,0.01000,2.451
+4,self_attn.q_proj,0.0000051861,0.01000,1.955
+4,self_attn.k_proj,0.0000010472,0.01000,1.968
+4,self_attn.v_proj,0.0000006435,0.01000,1.972
+4,self_attn.o_proj,0.0000004017,0.01000,0.385
+4,mlp.gate_proj,0.0000483229,0.01000,1.016
+4,mlp.up_proj,0.0000286641,0.01000,1.020
+4,mlp.down_proj,0.0000020155,0.01000,2.429
+5,self_attn.q_proj,0.0000053473,0.01000,1.822
+5,self_attn.k_proj,0.0000011562,0.01000,1.830
+5,self_attn.v_proj,0.0000007846,0.01000,1.836
+5,self_attn.o_proj,0.0000006263,0.01000,0.385
+5,mlp.gate_proj,0.0000895578,0.01000,1.053
+5,mlp.up_proj,0.0000575369,0.01000,1.054
+5,mlp.down_proj,0.0000016249,0.01000,2.437
+6,self_attn.q_proj,0.0000067485,0.01000,1.935
+6,self_attn.v_proj,0.0000005208,0.01000,1.946
+6,self_attn.k_proj,0.0000014808,0.01000,1.952
+6,self_attn.o_proj,0.0000003162,0.01000,0.382
+6,mlp.gate_proj,0.0000254618,0.01000,1.158
+6,mlp.up_proj,0.0000209385,0.01000,1.164
+6,mlp.down_proj,0.0000019938,0.01000,2.418
+7,self_attn.k_proj,0.0000006234,0.01000,1.908
+7,self_attn.q_proj,0.0000029763,0.01000,1.920
+7,self_attn.v_proj,0.0000004447,0.01000,1.923
+7,self_attn.o_proj,0.0000004287,0.01000,0.381
+7,mlp.up_proj,0.0000202503,0.01000,1.116
+7,mlp.gate_proj,0.0000216502,0.01000,1.122
+7,mlp.down_proj,0.0000021148,0.01000,2.480
+8,self_attn.v_proj,0.0000005914,0.01000,2.043
+8,self_attn.q_proj,0.0000066568,0.01000,2.059
+8,self_attn.k_proj,0.0000011667,0.01000,2.064
+8,self_attn.o_proj,0.0000005495,0.01000,0.381
+8,mlp.gate_proj,0.0000224026,0.01000,1.129
+8,mlp.up_proj,0.0000203852,0.01000,1.148
+8,mlp.down_proj,0.0000019636,0.01000,2.458
+9,self_attn.q_proj,0.0000049192,0.01000,2.061
+9,self_attn.k_proj,0.0000010630,0.01000,2.070
+9,self_attn.v_proj,0.0000005336,0.01000,2.074
+9,self_attn.o_proj,0.0000005241,0.01000,0.379
+9,mlp.gate_proj,0.0000203827,0.01000,1.181
+9,mlp.up_proj,0.0000195376,0.01000,1.185
+9,mlp.down_proj,0.0000019245,0.01000,2.483
+10,self_attn.v_proj,0.0000008478,0.01000,1.965
+10,self_attn.q_proj,0.0000054106,0.01000,1.980
+10,self_attn.k_proj,0.0000010833,0.01000,1.983
+10,self_attn.o_proj,0.0000008068,0.01000,0.396
+10,mlp.gate_proj,0.0000202889,0.01000,1.105
+10,mlp.up_proj,0.0000190990,0.01000,1.114
+10,mlp.down_proj,0.0000018507,0.01000,2.488
+11,self_attn.k_proj,0.0000010355,0.01000,1.862
+11,self_attn.q_proj,0.0000051612,0.01000,1.873
+11,self_attn.v_proj,0.0000006848,0.01000,1.875
+11,self_attn.o_proj,0.0000007517,0.01000,0.389
+11,mlp.up_proj,0.0000172346,0.01000,1.122
+11,mlp.gate_proj,0.0000195876,0.01000,1.124
+11,mlp.down_proj,0.0000015514,0.01000,2.472
+12,self_attn.q_proj,0.0000063280,0.01000,1.943
+12,self_attn.v_proj,0.0000006517,0.01000,1.954
+12,self_attn.k_proj,0.0000013597,0.01000,1.961
+12,self_attn.o_proj,0.0000005806,0.01000,0.382
+12,mlp.gate_proj,0.0000183718,0.01000,1.076
+12,mlp.up_proj,0.0000169639,0.01000,1.079
+12,mlp.down_proj,0.0000016565,0.01000,2.467
+13,self_attn.q_proj,0.0000038254,0.01000,2.083
+13,self_attn.k_proj,0.0000007774,0.01000,2.090
+13,self_attn.v_proj,0.0000005103,0.01000,2.095
+13,self_attn.o_proj,0.0000006030,0.01000,0.392
+13,mlp.gate_proj,0.0000168901,0.01000,1.022
+13,mlp.up_proj,0.0000162521,0.01000,1.021
+13,mlp.down_proj,0.0000014067,0.01000,2.448
+14,self_attn.q_proj,0.0000088065,0.01000,1.940
+14,self_attn.k_proj,0.0000013443,0.01000,1.962
+14,self_attn.v_proj,0.0000009059,0.01000,1.967
+14,self_attn.o_proj,0.0000005388,0.01000,0.381
+14,mlp.up_proj,0.0000183793,0.01000,1.114
+14,mlp.gate_proj,0.0000179331,0.01000,1.121
+14,mlp.down_proj,0.0000016678,0.01000,2.449
+15,self_attn.k_proj,0.0000009821,0.01000,1.949
+15,self_attn.q_proj,0.0000120981,0.01000,1.963
+15,self_attn.v_proj,0.0000008541,0.01000,1.965
+15,self_attn.o_proj,0.0000008848,0.01000,0.376
+15,mlp.up_proj,0.0000155239,0.01000,1.041
+15,mlp.gate_proj,0.0000162790,0.01000,1.049
+15,mlp.down_proj,0.0000014746,0.01000,2.457
+16,self_attn.q_proj,0.0000068590,0.01000,1.890
+16,self_attn.k_proj,0.0000012989,0.01000,1.905
+16,self_attn.v_proj,0.0000009590,0.01000,1.907
+16,self_attn.o_proj,0.0000007136,0.01000,0.382
+16,mlp.up_proj,0.0000179446,0.01000,1.035
+16,mlp.gate_proj,0.0000183787,0.01000,1.040
+16,mlp.down_proj,0.0000018648,0.01000,2.458
+17,self_attn.k_proj,0.0000008107,0.01000,1.999
+17,self_attn.q_proj,0.0000066983,0.01000,2.003
+17,self_attn.v_proj,0.0000013076,0.01000,2.012
+17,self_attn.o_proj,0.0000006854,0.01000,0.376
+17,mlp.up_proj,0.0000188351,0.01000,1.045
+17,mlp.gate_proj,0.0000189007,0.01000,1.054
+17,mlp.down_proj,0.0000023398,0.01000,2.455
+18,self_attn.q_proj,0.0000055498,0.01000,1.989
+18,self_attn.k_proj,0.0000009536,0.01000,2.001
+18,self_attn.v_proj,0.0000009467,0.01000,2.008
+18,self_attn.o_proj,0.0000010054,0.01000,0.388
+18,mlp.gate_proj,0.0000209988,0.01000,1.111
+18,mlp.up_proj,0.0000207743,0.01000,1.117
+18,mlp.down_proj,0.0000030687,0.01000,2.443
+19,self_attn.k_proj,0.0000011151,0.01000,1.916
+19,self_attn.q_proj,0.0000078458,0.01000,1.933
+19,self_attn.v_proj,0.0000018561,0.01000,1.934
+19,self_attn.o_proj,0.0000012008,0.01000,0.380
+19,mlp.up_proj,0.0000261958,0.01000,1.052
+19,mlp.gate_proj,0.0000247150,0.01000,1.062
+19,mlp.down_proj,0.0000052473,0.01000,2.458
+20,self_attn.q_proj,0.0000085666,0.01000,1.930
+20,self_attn.k_proj,0.0000013209,0.01000,1.942
+20,self_attn.v_proj,0.0000025131,0.01000,1.948
+20,self_attn.o_proj,0.0000019121,0.01000,0.383
+20,mlp.gate_proj,0.0000279776,0.01000,1.030
+20,mlp.up_proj,0.0000285871,0.01000,1.031
+20,mlp.down_proj,0.0000055100,0.01000,2.471
+21,self_attn.k_proj,0.0000012813,0.01000,1.997
+21,self_attn.q_proj,0.0000089735,0.01000,2.006
+21,self_attn.v_proj,0.0000023351,0.01000,2.010
+21,self_attn.o_proj,0.0000013078,0.01000,0.386
+21,mlp.up_proj,0.0000401897,0.01000,1.043
+21,mlp.gate_proj,0.0000403061,0.01000,1.050
+21,mlp.down_proj,0.0000088611,0.01000,2.445
+22,self_attn.q_proj,0.0000083670,0.01000,1.877
+22,self_attn.k_proj,0.0000014690,0.01000,1.891
+22,self_attn.v_proj,0.0000028189,0.01000,1.894
+22,self_attn.o_proj,0.0000017141,0.01000,0.386
+22,mlp.gate_proj,0.0000472013,0.01000,1.019
+22,mlp.up_proj,0.0000464103,0.01000,1.023
+22,mlp.down_proj,0.0000115764,0.01000,2.455
+23,self_attn.q_proj,0.0000104279,0.01000,1.886
+23,self_attn.k_proj,0.0000016164,0.01000,1.893
+23,self_attn.v_proj,0.0000035333,0.01000,1.897
+23,self_attn.o_proj,0.0000019307,0.01000,0.376
+23,mlp.up_proj,0.0000504941,0.01000,1.023
+23,mlp.gate_proj,0.0000487808,0.01000,1.030
+23,mlp.down_proj,0.0000135809,0.01000,2.460
+24,self_attn.q_proj,0.0000106897,0.01000,1.896
+24,self_attn.k_proj,0.0000017318,0.01000,1.904
+24,self_attn.v_proj,0.0000070466,0.01000,1.911
+24,self_attn.o_proj,0.0000025356,0.01000,0.383
+24,mlp.gate_proj,0.0000489959,0.01000,1.074
+24,mlp.up_proj,0.0000526075,0.01000,1.086
+24,mlp.down_proj,0.0000158640,0.01000,2.460
+25,self_attn.q_proj,0.0000103486,0.01000,1.940
+25,self_attn.k_proj,0.0000018338,0.01000,1.939
+25,self_attn.v_proj,0.0000106599,0.01000,1.938
+25,self_attn.o_proj,0.0000032838,0.01000,0.386
+25,mlp.gate_proj,0.0000488253,0.01000,1.071
+25,mlp.up_proj,0.0000559056,0.01000,1.071
+25,mlp.down_proj,0.0000200572,0.01000,2.464
+26,self_attn.v_proj,0.0000134646,0.01000,1.924
+26,self_attn.k_proj,0.0000018568,0.01000,1.937
+26,self_attn.q_proj,0.0000121274,0.01000,1.940
+26,self_attn.o_proj,0.0000024049,0.01000,0.388
+26,mlp.up_proj,0.0000554150,0.01000,1.125
+26,mlp.gate_proj,0.0000465803,0.01000,1.136
+26,mlp.down_proj,0.0000285185,0.01000,2.473
+27,self_attn.q_proj,0.0000120861,0.01000,1.860
+27,self_attn.v_proj,0.0000137723,0.01000,1.879
+27,self_attn.k_proj,0.0000019235,0.01000,1.888
+27,self_attn.o_proj,0.0000080364,0.01000,0.382
+27,mlp.gate_proj,0.0000615399,0.01000,1.081
+27,mlp.up_proj,0.0000640771,0.01000,1.085
+27,mlp.down_proj,0.0000351710,0.01000,2.455

qwen25-1p5b__gptq__openhermes__n512__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_mn8so5j0",
+    "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__n512__s0/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__n512__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
+}