Upload folder using huggingface_hub

.gitattributes

@@ -59,3 +59,4 @@ qwen25-1p5b__gptq__openhermes__n32__s0/tokenizer.json filter=lfs diff=lfs merge=
 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__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n512__s1/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T20:50:24.801036+00:00

qwen25-1p5b__gptq__openhermes__n512__s1/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__s1/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_jroj1e68",
+      "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__s1/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__s1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ace7e5592b6f88c6f8d9be38fdab157ba17e35094ed76263e62b5f7c8e515e5
+size 1149862904

qwen25-1p5b__gptq__openhermes__n512__s1/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000082516,0.01000,1.912
+0,self_attn.k_proj,0.0000011370,0.01000,1.930
+0,self_attn.v_proj,0.0000001346,0.01000,1.938
+0,self_attn.o_proj,0.0000002973,0.01000,0.381
+0,mlp.up_proj,0.0000023303,0.01000,1.097
+0,mlp.gate_proj,0.0000034011,0.01000,1.099
+0,mlp.down_proj,0.0000005314,0.01000,2.547
+1,self_attn.q_proj,0.0000012603,0.01000,1.932
+1,self_attn.k_proj,0.0000003756,0.01000,1.945
+1,self_attn.v_proj,0.0000000836,0.01000,1.954
+1,self_attn.o_proj,0.0000001195,0.01000,0.380
+1,mlp.gate_proj,0.0000946160,0.01000,1.012
+1,mlp.up_proj,0.0000768555,0.01000,1.014
+1,mlp.down_proj,0.0000032451,0.01000,2.466
+2,self_attn.q_proj,0.0000038909,0.01000,2.048
+2,self_attn.v_proj,0.0000003460,0.01000,2.074
+2,self_attn.k_proj,0.0000008458,0.01000,2.076
+2,self_attn.o_proj,0.0000002450,0.01000,0.378
+2,mlp.gate_proj,0.0000830534,0.01000,1.055
+2,mlp.up_proj,0.0000515437,0.01000,1.059
+2,mlp.down_proj,0.0000075941,0.01000,2.458
+3,self_attn.q_proj,0.0000039351,0.01000,1.991
+3,self_attn.v_proj,0.0000004461,0.01000,2.003
+3,self_attn.k_proj,0.0000008533,0.01000,2.008
+3,self_attn.o_proj,0.0000003463,0.01000,0.381
+3,mlp.gate_proj,0.0000683078,0.01000,1.074
+3,mlp.up_proj,0.0000358350,0.01000,1.073
+3,mlp.down_proj,0.0000016330,0.01000,2.538
+4,self_attn.q_proj,0.0000051513,0.01000,2.074
+4,self_attn.v_proj,0.0000006371,0.01000,2.084
+4,self_attn.k_proj,0.0000010412,0.01000,2.094
+4,self_attn.o_proj,0.0000004100,0.01000,0.383
+4,mlp.up_proj,0.0000284258,0.01000,1.278
+4,mlp.gate_proj,0.0000478467,0.01000,1.283
+4,mlp.down_proj,0.0000020034,0.01000,2.442
+5,self_attn.k_proj,0.0000011500,0.01000,1.884
+5,self_attn.q_proj,0.0000053111,0.01000,1.891
+5,self_attn.v_proj,0.0000007801,0.01000,1.899
+5,self_attn.o_proj,0.0000006178,0.01000,0.383
+5,mlp.gate_proj,0.0000889978,0.01000,1.094
+5,mlp.up_proj,0.0000572521,0.01000,1.099
+5,mlp.down_proj,0.0000016240,0.01000,2.435
+6,self_attn.q_proj,0.0000067000,0.01000,2.059
+6,self_attn.k_proj,0.0000014730,0.01000,2.074
+6,self_attn.v_proj,0.0000005180,0.01000,2.081
+6,self_attn.o_proj,0.0000003222,0.01000,0.380
+6,mlp.up_proj,0.0000207789,0.01000,1.074
+6,mlp.gate_proj,0.0000252565,0.01000,1.080
+6,mlp.down_proj,0.0000019693,0.01000,2.506
+7,self_attn.q_proj,0.0000029496,0.01000,2.058
+7,self_attn.v_proj,0.0000004394,0.01000,2.087
+7,self_attn.k_proj,0.0000006181,0.01000,2.096
+7,self_attn.o_proj,0.0000004266,0.01000,0.379
+7,mlp.up_proj,0.0000200036,0.01000,1.081
+7,mlp.gate_proj,0.0000213634,0.01000,1.085
+7,mlp.down_proj,0.0000020892,0.01000,2.440
+8,self_attn.q_proj,0.0000065875,0.01000,1.914
+8,self_attn.v_proj,0.0000005858,0.01000,1.917
+8,self_attn.k_proj,0.0000011536,0.01000,1.927
+8,self_attn.o_proj,0.0000005385,0.01000,0.384
+8,mlp.up_proj,0.0000201331,0.01000,1.168
+8,mlp.gate_proj,0.0000221140,0.01000,1.177
+8,mlp.down_proj,0.0000019394,0.01000,2.568
+9,self_attn.q_proj,0.0000048605,0.01000,1.904
+9,self_attn.k_proj,0.0000010520,0.01000,1.911
+9,self_attn.v_proj,0.0000005259,0.01000,1.918
+9,self_attn.o_proj,0.0000005207,0.01000,0.386
+9,mlp.up_proj,0.0000193244,0.01000,1.032
+9,mlp.gate_proj,0.0000201384,0.01000,1.033
+9,mlp.down_proj,0.0000018933,0.01000,2.429
+10,self_attn.q_proj,0.0000053218,0.01000,1.835
+10,self_attn.k_proj,0.0000010701,0.01000,1.840
+10,self_attn.v_proj,0.0000008351,0.01000,1.848
+10,self_attn.o_proj,0.0000007859,0.01000,0.379
+10,mlp.gate_proj,0.0000200097,0.01000,1.153
+10,mlp.up_proj,0.0000188404,0.01000,1.151
+10,mlp.down_proj,0.0000018230,0.01000,2.468
+11,self_attn.q_proj,0.0000050982,0.01000,1.976
+11,self_attn.k_proj,0.0000010215,0.01000,1.981
+11,self_attn.v_proj,0.0000006690,0.01000,1.988
+11,self_attn.o_proj,0.0000007414,0.01000,0.386
+11,mlp.up_proj,0.0000169963,0.01000,1.146
+11,mlp.gate_proj,0.0000193144,0.01000,1.147
+11,mlp.down_proj,0.0000015271,0.01000,2.466
+12,self_attn.q_proj,0.0000062308,0.01000,1.912
+12,self_attn.k_proj,0.0000013407,0.01000,1.913
+12,self_attn.v_proj,0.0000006404,0.01000,1.921
+12,self_attn.o_proj,0.0000005752,0.01000,0.385
+12,mlp.up_proj,0.0000167461,0.01000,1.098
+12,mlp.gate_proj,0.0000181554,0.01000,1.104
+12,mlp.down_proj,0.0000016335,0.01000,2.475
+13,self_attn.q_proj,0.0000037831,0.01000,1.975
+13,self_attn.v_proj,0.0000005025,0.01000,1.988
+13,self_attn.k_proj,0.0000007700,0.01000,1.996
+13,self_attn.o_proj,0.0000005947,0.01000,0.380
+13,mlp.gate_proj,0.0000167268,0.01000,1.046
+13,mlp.up_proj,0.0000161091,0.01000,1.053
+13,mlp.down_proj,0.0000013971,0.01000,2.469
+14,self_attn.q_proj,0.0000087182,0.01000,2.099
+14,self_attn.k_proj,0.0000013332,0.01000,2.106
+14,self_attn.v_proj,0.0000008985,0.01000,2.112
+14,self_attn.o_proj,0.0000005290,0.01000,0.400
+14,mlp.up_proj,0.0000182248,0.01000,1.092
+14,mlp.gate_proj,0.0000177637,0.01000,1.099
+14,mlp.down_proj,0.0000016534,0.01000,2.469
+15,self_attn.k_proj,0.0000009710,0.01000,2.037
+15,self_attn.q_proj,0.0000118860,0.01000,2.045
+15,self_attn.v_proj,0.0000008449,0.01000,2.049
+15,self_attn.o_proj,0.0000008841,0.01000,0.386
+15,mlp.up_proj,0.0000154303,0.01000,1.138
+15,mlp.gate_proj,0.0000161710,0.01000,1.146
+15,mlp.down_proj,0.0000014617,0.01000,2.452
+16,self_attn.q_proj,0.0000067836,0.01000,2.001
+16,self_attn.k_proj,0.0000012824,0.01000,2.001
+16,self_attn.v_proj,0.0000009479,0.01000,2.016
+16,self_attn.o_proj,0.0000007124,0.01000,0.386
+16,mlp.up_proj,0.0000178129,0.01000,1.108
+16,mlp.gate_proj,0.0000182413,0.01000,1.116
+16,mlp.down_proj,0.0000018446,0.01000,2.459
+17,self_attn.q_proj,0.0000066279,0.01000,2.109
+17,self_attn.k_proj,0.0000008046,0.01000,2.113
+17,self_attn.v_proj,0.0000012968,0.01000,2.120
+17,self_attn.o_proj,0.0000006579,0.01000,0.391
+17,mlp.up_proj,0.0000187463,0.01000,1.139
+17,mlp.gate_proj,0.0000188067,0.01000,1.143
+17,mlp.down_proj,0.0000023257,0.01000,2.486
+18,self_attn.q_proj,0.0000055175,0.01000,2.057
+18,self_attn.v_proj,0.0000009383,0.01000,2.066
+18,self_attn.k_proj,0.0000009448,0.01000,2.073
+18,self_attn.o_proj,0.0000009947,0.01000,0.386
+18,mlp.gate_proj,0.0000208386,0.01000,1.153
+18,mlp.up_proj,0.0000206193,0.01000,1.158
+18,mlp.down_proj,0.0000030336,0.01000,2.477
+19,self_attn.k_proj,0.0000011033,0.01000,2.222
+19,self_attn.q_proj,0.0000077657,0.01000,2.255
+19,self_attn.v_proj,0.0000018394,0.01000,2.253
+19,self_attn.o_proj,0.0000012042,0.01000,0.382
+19,mlp.up_proj,0.0000260283,0.01000,1.095
+19,mlp.gate_proj,0.0000245408,0.01000,1.103
+19,mlp.down_proj,0.0000052236,0.01000,2.476
+20,self_attn.q_proj,0.0000085239,0.01000,2.065
+20,self_attn.k_proj,0.0000013086,0.01000,2.081
+20,self_attn.v_proj,0.0000025065,0.01000,2.086
+20,self_attn.o_proj,0.0000018854,0.01000,0.387
+20,mlp.up_proj,0.0000283742,0.01000,1.249
+20,mlp.gate_proj,0.0000277748,0.01000,1.254
+20,mlp.down_proj,0.0000054476,0.01000,2.531
+21,self_attn.q_proj,0.0000088975,0.01000,2.159
+21,self_attn.v_proj,0.0000023113,0.01000,2.172
+21,self_attn.k_proj,0.0000012737,0.01000,2.180
+21,self_attn.o_proj,0.0000012581,0.01000,0.390
+21,mlp.gate_proj,0.0000400014,0.01000,1.173
+21,mlp.up_proj,0.0000399067,0.01000,1.175
+21,mlp.down_proj,0.0000087915,0.01000,2.479
+22,self_attn.q_proj,0.0000083049,0.01000,2.299
+22,self_attn.k_proj,0.0000014548,0.01000,2.325
+22,self_attn.v_proj,0.0000027888,0.01000,2.334
+22,self_attn.o_proj,0.0000017411,0.01000,0.399
+22,mlp.gate_proj,0.0000468470,0.01000,1.125
+22,mlp.up_proj,0.0000460683,0.01000,1.128
+22,mlp.down_proj,0.0000114153,0.01000,2.470
+23,self_attn.k_proj,0.0000016009,0.01000,2.123
+23,self_attn.q_proj,0.0000103127,0.01000,2.128
+23,self_attn.v_proj,0.0000034764,0.01000,2.129
+23,self_attn.o_proj,0.0000019099,0.01000,0.395
+23,mlp.gate_proj,0.0000484040,0.01000,1.139
+23,mlp.up_proj,0.0000501298,0.01000,1.145
+23,mlp.down_proj,0.0000134606,0.01000,2.472
+24,self_attn.q_proj,0.0000105908,0.01000,2.023
+24,self_attn.v_proj,0.0000069596,0.01000,2.024
+24,self_attn.k_proj,0.0000017168,0.01000,2.035
+24,self_attn.o_proj,0.0000026153,0.01000,0.379
+24,mlp.up_proj,0.0000521317,0.01000,1.107
+24,mlp.gate_proj,0.0000484859,0.01000,1.113
+24,mlp.down_proj,0.0000157147,0.01000,2.472
+25,self_attn.q_proj,0.0000102121,0.01000,2.047
+25,self_attn.v_proj,0.0000105608,0.01000,2.054
+25,self_attn.k_proj,0.0000018095,0.01000,2.061
+25,self_attn.o_proj,0.0000032361,0.01000,0.390
+25,mlp.gate_proj,0.0000482270,0.01000,1.185
+25,mlp.up_proj,0.0000552689,0.01000,1.191
+25,mlp.down_proj,0.0000198174,0.01000,2.468
+26,self_attn.q_proj,0.0000119943,0.01000,2.070
+26,self_attn.k_proj,0.0000018338,0.01000,2.080
+26,self_attn.v_proj,0.0000132851,0.01000,2.083
+26,self_attn.o_proj,0.0000023455,0.01000,0.387
+26,mlp.up_proj,0.0000551277,0.01000,1.129
+26,mlp.gate_proj,0.0000463129,0.01000,1.142
+26,mlp.down_proj,0.0000287738,0.01000,2.479
+27,self_attn.k_proj,0.0000019003,0.01000,2.096
+27,self_attn.q_proj,0.0000119898,0.01000,2.112
+27,self_attn.v_proj,0.0000136474,0.01000,2.115
+27,self_attn.o_proj,0.0000078715,0.01000,0.399
+27,mlp.up_proj,0.0000636627,0.01000,1.240
+27,mlp.gate_proj,0.0000610968,0.01000,1.241
+27,mlp.down_proj,0.0000346708,0.01000,2.450

qwen25-1p5b__gptq__openhermes__n512__s1/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_jroj1e68",
+    "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__s1/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__n512__s1/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
+}