Upload folder using huggingface_hub

.gitattributes

@@ -56,3 +56,4 @@ qwen25-1p5b__gptq__openhermes__n128__s0/tokenizer.json filter=lfs diff=lfs merge
 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__s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n32__s1/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T19:54:34.423356+00:00

qwen25-1p5b__gptq__openhermes__n32__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__n32__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_3h4zwuvm",
+      "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__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__n32__s1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7b8e36fb48d3c86f568a2e88a54559287b560bd5d7719c772d56852a10b918
+size 1149862904

qwen25-1p5b__gptq__openhermes__n32__s1/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0001213437,0.01000,1.871
+0,self_attn.v_proj,0.0000019975,0.01000,1.875
+0,self_attn.k_proj,0.0000169272,0.01000,1.881
+0,self_attn.o_proj,0.0000046327,0.01000,0.374
+0,mlp.up_proj,0.0000362972,0.01000,0.992
+0,mlp.gate_proj,0.0000529442,0.01000,0.993
+0,mlp.down_proj,0.0000069456,0.01000,2.459
+1,self_attn.k_proj,0.0000057712,0.01000,1.897
+1,self_attn.q_proj,0.0000194772,0.01000,1.903
+1,self_attn.v_proj,0.0000012887,0.01000,1.910
+1,self_attn.o_proj,0.0000018317,0.01000,0.372
+1,mlp.up_proj,0.0011917753,0.01000,0.990
+1,mlp.gate_proj,0.0014642454,0.01000,0.997
+1,mlp.down_proj,0.0000450234,0.01000,2.402
+2,self_attn.q_proj,0.0000593901,0.01000,1.792
+2,self_attn.v_proj,0.0000053220,0.01000,1.801
+2,self_attn.k_proj,0.0000129909,0.01000,1.801
+2,self_attn.o_proj,0.0000036363,0.01000,0.367
+2,mlp.gate_proj,0.0012723301,0.01000,0.988
+2,mlp.up_proj,0.0007934332,0.01000,0.994
+2,mlp.down_proj,0.0000992175,0.01000,2.406
+3,self_attn.q_proj,0.0000598471,0.01000,1.853
+3,self_attn.v_proj,0.0000068012,0.01000,1.852
+3,self_attn.k_proj,0.0000129376,0.01000,1.857
+3,self_attn.o_proj,0.0000052380,0.01000,0.378
+3,mlp.gate_proj,0.0010377485,0.01000,1.000
+3,mlp.up_proj,0.0005485014,0.01000,1.001
+3,mlp.down_proj,0.0000201480,0.01000,2.444
+4,self_attn.q_proj,0.0000778170,0.01000,1.796
+4,self_attn.v_proj,0.0000096834,0.01000,1.794
+4,self_attn.k_proj,0.0000156830,0.01000,1.800
+4,self_attn.o_proj,0.0000060492,0.01000,0.367
+4,mlp.gate_proj,0.0007233016,0.01000,1.019
+4,mlp.up_proj,0.0004329276,0.01000,1.028
+4,mlp.down_proj,0.0000258323,0.01000,2.404
+5,self_attn.k_proj,0.0000172384,0.01000,1.801
+5,self_attn.v_proj,0.0000119149,0.01000,1.815
+5,self_attn.q_proj,0.0000800007,0.01000,1.820
+5,self_attn.o_proj,0.0000093903,0.01000,0.372
+5,mlp.gate_proj,0.0013453305,0.01000,0.970
+5,mlp.up_proj,0.0008695218,0.01000,0.971
+5,mlp.down_proj,0.0000196609,0.01000,2.412
+6,self_attn.q_proj,0.0000996261,0.01000,1.830
+6,self_attn.k_proj,0.0000219471,0.01000,1.836
+6,self_attn.v_proj,0.0000077410,0.01000,1.840
+6,self_attn.o_proj,0.0000046449,0.01000,0.374
+6,mlp.gate_proj,0.0003783513,0.01000,0.989
+6,mlp.up_proj,0.0003121544,0.01000,0.992
+6,mlp.down_proj,0.0000248240,0.01000,2.406
+7,self_attn.q_proj,0.0000436570,0.01000,1.787
+7,self_attn.k_proj,0.0000090998,0.01000,1.792
+7,self_attn.v_proj,0.0000065307,0.01000,1.797
+7,self_attn.o_proj,0.0000059975,0.01000,0.375
+7,mlp.up_proj,0.0002978103,0.01000,0.967
+7,mlp.gate_proj,0.0003175125,0.01000,0.971
+7,mlp.down_proj,0.0000267619,0.01000,2.403
+8,self_attn.q_proj,0.0000966416,0.01000,1.854
+8,self_attn.v_proj,0.0000087171,0.01000,1.860
+8,self_attn.k_proj,0.0000169522,0.01000,1.867
+8,self_attn.o_proj,0.0000079720,0.01000,0.371
+8,mlp.up_proj,0.0003011833,0.01000,0.980
+8,mlp.gate_proj,0.0003292711,0.01000,0.984
+8,mlp.down_proj,0.0000249626,0.01000,2.389
+9,self_attn.k_proj,0.0000155297,0.01000,1.781
+9,self_attn.q_proj,0.0000720094,0.01000,1.788
+9,self_attn.v_proj,0.0000078755,0.01000,1.786
+9,self_attn.o_proj,0.0000077620,0.01000,0.373
+9,mlp.gate_proj,0.0003006531,0.01000,1.023
+9,mlp.up_proj,0.0002892284,0.01000,1.026
+9,mlp.down_proj,0.0000248564,0.01000,2.397
+10,self_attn.q_proj,0.0000788407,0.01000,1.888
+10,self_attn.v_proj,0.0000124208,0.01000,1.892
+10,self_attn.k_proj,0.0000158162,0.01000,1.894
+10,self_attn.o_proj,0.0000113198,0.01000,0.370
+10,mlp.gate_proj,0.0002974950,0.01000,0.987
+10,mlp.up_proj,0.0002807911,0.01000,0.992
+10,mlp.down_proj,0.0000237724,0.01000,2.411
+11,self_attn.k_proj,0.0000150672,0.01000,1.830
+11,self_attn.v_proj,0.0000099482,0.01000,1.837
+11,self_attn.q_proj,0.0000752388,0.01000,1.839
+11,self_attn.o_proj,0.0000105029,0.01000,0.370
+11,mlp.up_proj,0.0002509114,0.01000,0.972
+11,mlp.gate_proj,0.0002843786,0.01000,0.979
+11,mlp.down_proj,0.0000194994,0.01000,2.409
+12,self_attn.v_proj,0.0000094491,0.01000,1.872
+12,self_attn.k_proj,0.0000194515,0.01000,1.891
+12,self_attn.q_proj,0.0000912025,0.01000,1.896
+12,self_attn.o_proj,0.0000082008,0.01000,0.372
+12,mlp.up_proj,0.0002494369,0.01000,1.003
+12,mlp.gate_proj,0.0002703103,0.01000,1.003
+12,mlp.down_proj,0.0000218429,0.01000,2.407
+13,self_attn.q_proj,0.0000566200,0.01000,1.811
+13,self_attn.k_proj,0.0000115322,0.01000,1.815
+13,self_attn.v_proj,0.0000075212,0.01000,1.825
+13,self_attn.o_proj,0.0000090066,0.01000,0.374
+13,mlp.gate_proj,0.0002513697,0.01000,1.110
+13,mlp.up_proj,0.0002422466,0.01000,1.115
+13,mlp.down_proj,0.0000191333,0.01000,2.399
+14,self_attn.q_proj,0.0001295984,0.01000,1.847
+14,self_attn.v_proj,0.0000134017,0.01000,1.864
+14,self_attn.k_proj,0.0000197907,0.01000,1.868
+14,self_attn.o_proj,0.0000078179,0.01000,0.368
+14,mlp.up_proj,0.0002753537,0.01000,1.015
+14,mlp.gate_proj,0.0002683711,0.01000,1.019
+14,mlp.down_proj,0.0000227412,0.01000,2.404
+15,self_attn.q_proj,0.0001739811,0.01000,1.797
+15,self_attn.k_proj,0.0000143892,0.01000,1.807
+15,self_attn.v_proj,0.0000126285,0.01000,1.812
+15,self_attn.o_proj,0.0000131131,0.01000,0.371
+15,mlp.gate_proj,0.0002399719,0.01000,1.028
+15,mlp.up_proj,0.0002292688,0.01000,1.032
+15,mlp.down_proj,0.0000190099,0.01000,2.438
+16,self_attn.k_proj,0.0000186240,0.01000,1.858
+16,self_attn.v_proj,0.0000139961,0.01000,1.856
+16,self_attn.q_proj,0.0001000046,0.01000,1.871
+16,self_attn.o_proj,0.0000097801,0.01000,0.367
+16,mlp.up_proj,0.0002657080,0.01000,1.030
+16,mlp.gate_proj,0.0002705322,0.01000,1.032
+16,mlp.down_proj,0.0000245061,0.01000,2.393
+17,self_attn.q_proj,0.0000979493,0.01000,1.846
+17,self_attn.k_proj,0.0000118552,0.01000,1.857
+17,self_attn.v_proj,0.0000193658,0.01000,1.861
+17,self_attn.o_proj,0.0000094563,0.01000,0.369
+17,mlp.up_proj,0.0002812643,0.01000,0.973
+17,mlp.gate_proj,0.0002813556,0.01000,0.981
+17,mlp.down_proj,0.0000314421,0.01000,2.415
+18,self_attn.k_proj,0.0000140003,0.01000,1.832
+18,self_attn.q_proj,0.0000815372,0.01000,1.836
+18,self_attn.v_proj,0.0000139691,0.01000,1.842
+18,self_attn.o_proj,0.0000150970,0.01000,0.372
+18,mlp.up_proj,0.0003115625,0.01000,0.964
+18,mlp.gate_proj,0.0003135508,0.01000,0.971
+18,mlp.down_proj,0.0000418756,0.01000,2.397
+19,self_attn.k_proj,0.0000163900,0.01000,1.799
+19,self_attn.q_proj,0.0001160703,0.01000,1.801
+19,self_attn.v_proj,0.0000277413,0.01000,1.805
+19,self_attn.o_proj,0.0000181930,0.01000,0.374
+19,mlp.up_proj,0.0003931882,0.01000,1.177
+19,mlp.gate_proj,0.0003686559,0.01000,1.207
+19,mlp.down_proj,0.0000710458,0.01000,2.502
+20,self_attn.q_proj,0.0001274588,0.01000,2.955
+20,self_attn.v_proj,0.0000374789,0.01000,2.984
+20,self_attn.k_proj,0.0000192962,0.01000,3.003
+20,self_attn.o_proj,0.0000274514,0.01000,0.407
+20,mlp.up_proj,0.0004241691,0.01000,1.256
+20,mlp.gate_proj,0.0004136471,0.01000,1.310
+20,mlp.down_proj,0.0000713145,0.01000,2.422
+21,self_attn.v_proj,0.0000340118,0.01000,1.775
+21,self_attn.k_proj,0.0000183913,0.01000,1.781
+21,self_attn.q_proj,0.0001303894,0.01000,1.789
+21,self_attn.o_proj,0.0000176822,0.01000,0.367
+21,mlp.gate_proj,0.0005914783,0.01000,0.974
+21,mlp.up_proj,0.0005930968,0.01000,0.975
+21,mlp.down_proj,0.0001136571,0.01000,2.411
+22,self_attn.v_proj,0.0000408799,0.01000,2.045
+22,self_attn.q_proj,0.0001220694,0.01000,2.073
+22,self_attn.k_proj,0.0000211820,0.01000,2.081
+22,self_attn.o_proj,0.0000248855,0.01000,0.388
+22,mlp.up_proj,0.0006832507,0.01000,1.125
+22,mlp.gate_proj,0.0006878619,0.01000,1.134
+22,mlp.down_proj,0.0001456856,0.01000,2.405
+23,self_attn.q_proj,0.0001517066,0.01000,1.799
+23,self_attn.v_proj,0.0000516067,0.01000,1.805
+23,self_attn.k_proj,0.0000233489,0.01000,1.811
+23,self_attn.o_proj,0.0000279227,0.01000,0.369
+23,mlp.up_proj,0.0007397549,0.01000,1.055
+23,mlp.gate_proj,0.0007097526,0.01000,1.060
+23,mlp.down_proj,0.0001613011,0.01000,2.413
+24,self_attn.v_proj,0.0001028710,0.01000,1.815
+24,self_attn.q_proj,0.0001558718,0.01000,1.825
+24,self_attn.k_proj,0.0000250866,0.01000,1.830
+24,self_attn.o_proj,0.0000369221,0.01000,0.374
+24,mlp.gate_proj,0.0007145264,0.01000,0.979
+24,mlp.up_proj,0.0007692280,0.01000,0.980
+24,mlp.down_proj,0.0001897003,0.01000,2.386
+25,self_attn.k_proj,0.0000269931,0.01000,1.791
+25,self_attn.v_proj,0.0001586075,0.01000,1.799
+25,self_attn.q_proj,0.0001529976,0.01000,1.806
+25,self_attn.o_proj,0.0000472357,0.01000,0.371
+25,mlp.up_proj,0.0008159271,0.01000,0.979
+25,mlp.gate_proj,0.0007110998,0.01000,0.982
+25,mlp.down_proj,0.0002410873,0.01000,2.408
+26,self_attn.k_proj,0.0000272479,0.01000,1.843
+26,self_attn.v_proj,0.0001991075,0.01000,1.842
+26,self_attn.q_proj,0.0001772100,0.01000,1.849
+26,self_attn.o_proj,0.0000302291,0.01000,0.376
+26,mlp.up_proj,0.0008131132,0.01000,0.977
+26,mlp.gate_proj,0.0006811060,0.01000,0.983
+26,mlp.down_proj,0.0003805794,0.01000,2.416
+27,self_attn.k_proj,0.0000279460,0.01000,1.789
+27,self_attn.v_proj,0.0002027446,0.01000,1.796
+27,self_attn.q_proj,0.0001764442,0.01000,1.805
+27,self_attn.o_proj,0.0001056461,0.01000,0.374
+27,mlp.up_proj,0.0009410910,0.01000,1.037
+27,mlp.gate_proj,0.0009029990,0.01000,1.043
+27,mlp.down_proj,0.0004197340,0.01000,2.412

qwen25-1p5b__gptq__openhermes__n32__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_3h4zwuvm",
+    "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__s1/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__n32__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
+}