Upload folder using huggingface_hub

.gitattributes

@@ -54,3 +54,4 @@ qwen25-1p5b__awq__wikitext2__n512__s1/tokenizer.json filter=lfs diff=lfs merge=l
 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__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__n128__s2/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T20:20:59.427253+00:00

qwen25-1p5b__gptq__openhermes__n128__s2/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__s2/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_de9miqnr",
+      "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__s2/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__s2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51858316d599d12918db331ddcdf923bc3cb9dfa6806abee5bc3bc258dcb822
+size 1149862904

qwen25-1p5b__gptq__openhermes__n128__s2/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000319646,0.01000,1.842
+0,self_attn.v_proj,0.0000005211,0.01000,1.857
+0,self_attn.k_proj,0.0000044181,0.01000,1.864
+0,self_attn.o_proj,0.0000011771,0.01000,0.376
+0,mlp.up_proj,0.0000091947,0.01000,1.038
+0,mlp.gate_proj,0.0000134176,0.01000,1.045
+0,mlp.down_proj,0.0000019787,0.01000,2.443
+1,self_attn.q_proj,0.0000049392,0.01000,2.024
+1,self_attn.k_proj,0.0000014705,0.01000,2.037
+1,self_attn.v_proj,0.0000003274,0.01000,2.047
+1,self_attn.o_proj,0.0000004704,0.01000,0.388
+1,mlp.up_proj,0.0003023931,0.01000,1.049
+1,mlp.gate_proj,0.0003719909,0.01000,1.060
+1,mlp.down_proj,0.0000121116,0.01000,2.471
+2,self_attn.q_proj,0.0000152563,0.01000,1.904
+2,self_attn.k_proj,0.0000033363,0.01000,1.906
+2,self_attn.v_proj,0.0000013520,0.01000,1.920
+2,self_attn.o_proj,0.0000009652,0.01000,0.387
+2,mlp.up_proj,0.0002022610,0.01000,1.049
+2,mlp.gate_proj,0.0003254751,0.01000,1.053
+2,mlp.down_proj,0.0000249425,0.01000,2.480
+3,self_attn.v_proj,0.0000017420,0.01000,2.251
+3,self_attn.q_proj,0.0000153622,0.01000,2.278
+3,self_attn.k_proj,0.0000033193,0.01000,2.283
+3,self_attn.o_proj,0.0000013310,0.01000,0.399
+3,mlp.up_proj,0.0001400400,0.01000,1.273
+3,mlp.gate_proj,0.0002659822,0.01000,1.304
+3,mlp.down_proj,0.0000058773,0.01000,2.488
+4,self_attn.k_proj,0.0000040419,0.01000,2.168
+4,self_attn.q_proj,0.0000200073,0.01000,2.186
+4,self_attn.v_proj,0.0000024775,0.01000,2.191
+4,self_attn.o_proj,0.0000015609,0.01000,0.381
+4,mlp.up_proj,0.0001108060,0.01000,1.215
+4,mlp.gate_proj,0.0001859972,0.01000,1.226
+4,mlp.down_proj,0.0000073995,0.01000,2.468
+5,self_attn.q_proj,0.0000206139,0.01000,2.230
+5,self_attn.k_proj,0.0000044533,0.01000,2.265
+5,self_attn.v_proj,0.0000030414,0.01000,2.272
+5,self_attn.o_proj,0.0000024222,0.01000,0.385
+5,mlp.up_proj,0.0002224376,0.01000,1.047
+5,mlp.gate_proj,0.0003453945,0.01000,1.060
+5,mlp.down_proj,0.0000058981,0.01000,2.443
+6,self_attn.q_proj,0.0000258748,0.01000,1.960
+6,self_attn.v_proj,0.0000020174,0.01000,1.964
+6,self_attn.k_proj,0.0000056834,0.01000,1.969
+6,self_attn.o_proj,0.0000012291,0.01000,0.382
+6,mlp.up_proj,0.0000805577,0.01000,1.036
+6,mlp.gate_proj,0.0000978037,0.01000,1.046
+6,mlp.down_proj,0.0000072550,0.01000,2.479
+7,self_attn.k_proj,0.0000023802,0.01000,2.101
+7,self_attn.q_proj,0.0000113747,0.01000,2.118
+7,self_attn.v_proj,0.0000017001,0.01000,2.112
+7,self_attn.o_proj,0.0000016333,0.01000,0.394
+7,mlp.gate_proj,0.0000826219,0.01000,1.127
+7,mlp.up_proj,0.0000774400,0.01000,1.130
+7,mlp.down_proj,0.0000077422,0.01000,2.478
+8,self_attn.q_proj,0.0000253171,0.01000,1.942
+8,self_attn.v_proj,0.0000022720,0.01000,1.954
+8,self_attn.k_proj,0.0000044455,0.01000,1.966
+8,self_attn.o_proj,0.0000021184,0.01000,0.388
+8,mlp.up_proj,0.0000782201,0.01000,1.121
+8,mlp.gate_proj,0.0000857329,0.01000,1.131
+8,mlp.down_proj,0.0000071938,0.01000,2.460
+9,self_attn.k_proj,0.0000040673,0.01000,2.235
+9,self_attn.q_proj,0.0000188360,0.01000,2.249
+9,self_attn.v_proj,0.0000020412,0.01000,2.250
+9,self_attn.o_proj,0.0000020255,0.01000,0.390
+9,mlp.up_proj,0.0000748956,0.01000,1.292
+9,mlp.gate_proj,0.0000779964,0.01000,1.297
+9,mlp.down_proj,0.0000070629,0.01000,2.490
+10,self_attn.v_proj,0.0000032345,0.01000,2.309
+10,self_attn.k_proj,0.0000041419,0.01000,2.344
+10,self_attn.q_proj,0.0000206274,0.01000,2.363
+10,self_attn.o_proj,0.0000030455,0.01000,0.391
+10,mlp.gate_proj,0.0000776552,0.01000,1.291
+10,mlp.up_proj,0.0000731292,0.01000,1.302
+10,mlp.down_proj,0.0000067923,0.01000,2.472
+11,self_attn.k_proj,0.0000039650,0.01000,2.066
+11,self_attn.q_proj,0.0000197664,0.01000,2.082
+11,self_attn.v_proj,0.0000026011,0.01000,2.086
+11,self_attn.o_proj,0.0000027957,0.01000,0.383
+11,mlp.gate_proj,0.0000750577,0.01000,1.107
+11,mlp.up_proj,0.0000660749,0.01000,1.109
+11,mlp.down_proj,0.0000056842,0.01000,2.483
+12,self_attn.q_proj,0.0000240605,0.01000,1.917
+12,self_attn.k_proj,0.0000051733,0.01000,1.923
+12,self_attn.v_proj,0.0000024800,0.01000,1.928
+12,self_attn.o_proj,0.0000022580,0.01000,0.386
+12,mlp.gate_proj,0.0000704571,0.01000,1.075
+12,mlp.up_proj,0.0000649018,0.01000,1.073
+12,mlp.down_proj,0.0000061569,0.01000,2.452
+13,self_attn.k_proj,0.0000029875,0.01000,2.131
+13,self_attn.v_proj,0.0000019626,0.01000,2.138
+13,self_attn.q_proj,0.0000146839,0.01000,2.139
+13,self_attn.o_proj,0.0000023179,0.01000,0.389
+13,mlp.gate_proj,0.0000652862,0.01000,1.306
+13,mlp.up_proj,0.0000628155,0.01000,1.310
+13,mlp.down_proj,0.0000053307,0.01000,2.474
+14,self_attn.k_proj,0.0000052121,0.01000,2.086
+14,self_attn.q_proj,0.0000339141,0.01000,2.106
+14,self_attn.v_proj,0.0000034786,0.01000,2.109
+14,self_attn.o_proj,0.0000021510,0.01000,0.395
+14,mlp.up_proj,0.0000712101,0.01000,1.275
+14,mlp.gate_proj,0.0000693933,0.01000,1.270
+14,mlp.down_proj,0.0000063415,0.01000,2.536
+15,self_attn.q_proj,0.0000461348,0.01000,2.044
+15,self_attn.v_proj,0.0000033089,0.01000,2.063
+15,self_attn.k_proj,0.0000037807,0.01000,2.063
+15,self_attn.o_proj,0.0000034658,0.01000,0.391
+15,mlp.gate_proj,0.0000628773,0.01000,1.120
+15,mlp.up_proj,0.0000599944,0.01000,1.124
+15,mlp.down_proj,0.0000055154,0.01000,2.471
+16,self_attn.q_proj,0.0000264368,0.01000,2.020
+16,self_attn.v_proj,0.0000037057,0.01000,2.025
+16,self_attn.k_proj,0.0000050082,0.01000,2.032
+16,self_attn.o_proj,0.0000027638,0.01000,0.377
+16,mlp.up_proj,0.0000695624,0.01000,1.108
+16,mlp.gate_proj,0.0000710929,0.01000,1.112
+16,mlp.down_proj,0.0000069760,0.01000,2.459
+17,self_attn.k_proj,0.0000031100,0.01000,2.050
+17,self_attn.q_proj,0.0000257555,0.01000,2.049
+17,self_attn.v_proj,0.0000050330,0.01000,2.056
+17,self_attn.o_proj,0.0000026143,0.01000,0.382
+17,mlp.gate_proj,0.0000731819,0.01000,1.094
+17,mlp.up_proj,0.0000730208,0.01000,1.101
+17,mlp.down_proj,0.0000087921,0.01000,2.462
+18,self_attn.q_proj,0.0000214385,0.01000,2.019
+18,self_attn.v_proj,0.0000036513,0.01000,2.037
+18,self_attn.k_proj,0.0000036734,0.01000,2.045
+18,self_attn.o_proj,0.0000039668,0.01000,0.387
+18,mlp.gate_proj,0.0000813083,0.01000,1.065
+18,mlp.up_proj,0.0000805724,0.01000,1.064
+18,mlp.down_proj,0.0000115615,0.01000,2.444
+19,self_attn.q_proj,0.0000302223,0.01000,1.954
+19,self_attn.v_proj,0.0000071573,0.01000,1.968
+19,self_attn.k_proj,0.0000042741,0.01000,1.971
+19,self_attn.o_proj,0.0000046974,0.01000,0.383
+19,mlp.gate_proj,0.0000955085,0.01000,1.102
+19,mlp.up_proj,0.0001015432,0.01000,1.104
+19,mlp.down_proj,0.0000197997,0.01000,2.466
+20,self_attn.q_proj,0.0000330843,0.01000,1.967
+20,self_attn.k_proj,0.0000050683,0.01000,1.971
+20,self_attn.v_proj,0.0000097376,0.01000,1.984
+20,self_attn.o_proj,0.0000074887,0.01000,0.384
+20,mlp.gate_proj,0.0001080088,0.01000,1.081
+20,mlp.up_proj,0.0001105882,0.01000,1.086
+20,mlp.down_proj,0.0000207131,0.01000,2.472
+21,self_attn.q_proj,0.0000345654,0.01000,2.082
+21,self_attn.v_proj,0.0000089766,0.01000,2.089
+21,self_attn.k_proj,0.0000049212,0.01000,2.092
+21,self_attn.o_proj,0.0000048552,0.01000,0.381
+21,mlp.up_proj,0.0001557980,0.01000,1.093
+21,mlp.gate_proj,0.0001560528,0.01000,1.102
+21,mlp.down_proj,0.0000330124,0.01000,2.496
+22,self_attn.q_proj,0.0000323338,0.01000,1.978
+22,self_attn.k_proj,0.0000056593,0.01000,1.996
+22,self_attn.v_proj,0.0000108677,0.01000,2.000
+22,self_attn.o_proj,0.0000068152,0.01000,0.385
+22,mlp.up_proj,0.0001801820,0.01000,1.102
+22,mlp.gate_proj,0.0001827171,0.01000,1.113
+22,mlp.down_proj,0.0000429365,0.01000,2.449
+23,self_attn.q_proj,0.0000401502,0.01000,1.947
+23,self_attn.k_proj,0.0000062219,0.01000,1.965
+23,self_attn.v_proj,0.0000136050,0.01000,1.969
+23,self_attn.o_proj,0.0000076198,0.01000,0.378
+23,mlp.up_proj,0.0001958504,0.01000,1.111
+23,mlp.gate_proj,0.0001888091,0.01000,1.117
+23,mlp.down_proj,0.0000497401,0.01000,2.457
+24,self_attn.q_proj,0.0000412810,0.01000,1.991
+24,self_attn.v_proj,0.0000271538,0.01000,1.992
+24,self_attn.k_proj,0.0000066874,0.01000,1.998
+24,self_attn.o_proj,0.0000101747,0.01000,0.382
+24,mlp.gate_proj,0.0001889496,0.01000,1.095
+24,mlp.up_proj,0.0002034370,0.01000,1.104
+24,mlp.down_proj,0.0000579189,0.01000,2.444
+25,self_attn.k_proj,0.0000070681,0.01000,1.919
+25,self_attn.q_proj,0.0000398281,0.01000,1.921
+25,self_attn.v_proj,0.0000412860,0.01000,1.924
+25,self_attn.o_proj,0.0000127847,0.01000,0.382
+25,mlp.gate_proj,0.0001877584,0.01000,1.093
+25,mlp.up_proj,0.0002150490,0.01000,1.094
+25,mlp.down_proj,0.0000726970,0.01000,2.459
+26,self_attn.q_proj,0.0000467536,0.01000,1.897
+26,self_attn.v_proj,0.0000520437,0.01000,1.907
+26,self_attn.k_proj,0.0000071411,0.01000,1.914
+26,self_attn.o_proj,0.0000090498,0.01000,0.384
+26,mlp.gate_proj,0.0001795689,0.01000,1.065
+26,mlp.up_proj,0.0002137869,0.01000,1.066
+26,mlp.down_proj,0.0001074763,0.01000,2.460
+27,self_attn.q_proj,0.0000465483,0.01000,1.936
+27,self_attn.k_proj,0.0000073802,0.01000,1.938
+27,self_attn.v_proj,0.0000530093,0.01000,1.953
+27,self_attn.o_proj,0.0000307262,0.01000,0.383
+27,mlp.gate_proj,0.0002353672,0.01000,1.077
+27,mlp.up_proj,0.0002453577,0.01000,1.079
+27,mlp.down_proj,0.0001264414,0.01000,2.466

qwen25-1p5b__gptq__openhermes__n128__s2/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_de9miqnr",
+    "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__s2/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__n128__s2/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
+}