Upload folder using huggingface_hub

.gitattributes

@@ -60,3 +60,4 @@ qwen25-1p5b__gptq__openhermes__n32__s1/tokenizer.json filter=lfs diff=lfs merge=
 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__s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen25-1p5b__gptq__openhermes__n512__s2/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-30T21:05:04.474595+00:00

qwen25-1p5b__gptq__openhermes__n512__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__n512__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_tumiwt6x",
+      "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__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__n512__s2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4683cfabffe52968c2e62853620da77ba56944cc486a7656fa72208826ba0eed
+size 1149862904

qwen25-1p5b__gptq__openhermes__n512__s2/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000001357,0.01000,2.055
+0,self_attn.k_proj,0.0000011500,0.01000,2.058
+0,self_attn.q_proj,0.0000083572,0.01000,2.068
+0,self_attn.o_proj,0.0000002990,0.01000,0.379
+0,mlp.up_proj,0.0000023416,0.01000,1.100
+0,mlp.gate_proj,0.0000034177,0.01000,1.107
+0,mlp.down_proj,0.0000005354,0.01000,2.464
+1,self_attn.v_proj,0.0000000840,0.01000,1.934
+1,self_attn.k_proj,0.0000003779,0.01000,1.938
+1,self_attn.q_proj,0.0000012688,0.01000,1.948
+1,self_attn.o_proj,0.0000001206,0.01000,0.384
+1,mlp.up_proj,0.0000774157,0.01000,1.056
+1,mlp.gate_proj,0.0000953502,0.01000,1.065
+1,mlp.down_proj,0.0000032128,0.01000,2.442
+2,self_attn.v_proj,0.0000003494,0.01000,1.991
+2,self_attn.q_proj,0.0000039287,0.01000,2.000
+2,self_attn.k_proj,0.0000008547,0.01000,1.999
+2,self_attn.o_proj,0.0000002459,0.01000,0.381
+2,mlp.gate_proj,0.0000838052,0.01000,1.027
+2,mlp.up_proj,0.0000519523,0.01000,1.034
+2,mlp.down_proj,0.0000076335,0.01000,2.452
+3,self_attn.k_proj,0.0000008600,0.01000,2.028
+3,self_attn.q_proj,0.0000039696,0.01000,2.034
+3,self_attn.v_proj,0.0000004509,0.01000,2.041
+3,self_attn.o_proj,0.0000003491,0.01000,0.380
+3,mlp.gate_proj,0.0000689681,0.01000,1.175
+3,mlp.up_proj,0.0000361718,0.01000,1.178
+3,mlp.down_proj,0.0000016566,0.01000,2.470
+4,self_attn.k_proj,0.0000010541,0.01000,1.962
+4,self_attn.q_proj,0.0000052028,0.01000,1.978
+4,self_attn.v_proj,0.0000006443,0.01000,1.978
+4,self_attn.o_proj,0.0000004100,0.01000,0.387
+4,mlp.gate_proj,0.0000484046,0.01000,1.097
+4,mlp.up_proj,0.0000287086,0.01000,1.101
+4,mlp.down_proj,0.0000020212,0.01000,2.453
+5,self_attn.k_proj,0.0000011636,0.01000,1.953
+5,self_attn.q_proj,0.0000053671,0.01000,1.958
+5,self_attn.v_proj,0.0000007875,0.01000,1.972
+5,self_attn.o_proj,0.0000006265,0.01000,0.373
+5,mlp.gate_proj,0.0000897115,0.01000,1.039
+5,mlp.up_proj,0.0000576589,0.01000,1.043
+5,mlp.down_proj,0.0000016259,0.01000,2.445
+6,self_attn.q_proj,0.0000067517,0.01000,1.949
+6,self_attn.v_proj,0.0000005261,0.01000,1.946
+6,self_attn.k_proj,0.0000014861,0.01000,1.949
+6,self_attn.o_proj,0.0000003167,0.01000,0.377
+6,mlp.gate_proj,0.0000255282,0.01000,1.098
+6,mlp.up_proj,0.0000209791,0.01000,1.099
+6,mlp.down_proj,0.0000020015,0.01000,2.458
+7,self_attn.k_proj,0.0000006259,0.01000,1.957
+7,self_attn.q_proj,0.0000029878,0.01000,1.960
+7,self_attn.v_proj,0.0000004453,0.01000,1.971
+7,self_attn.o_proj,0.0000004340,0.01000,0.387
+7,mlp.gate_proj,0.0000217184,0.01000,1.071
+7,mlp.up_proj,0.0000203404,0.01000,1.072
+7,mlp.down_proj,0.0000021308,0.01000,2.462
+8,self_attn.v_proj,0.0000005944,0.01000,2.131
+8,self_attn.q_proj,0.0000066846,0.01000,2.138
+8,self_attn.k_proj,0.0000011701,0.01000,2.146
+8,self_attn.o_proj,0.0000005490,0.01000,0.386
+8,mlp.gate_proj,0.0000225093,0.01000,1.151
+8,mlp.up_proj,0.0000204888,0.01000,1.155
+8,mlp.down_proj,0.0000019721,0.01000,2.478
+9,self_attn.v_proj,0.0000005366,0.01000,1.867
+9,self_attn.q_proj,0.0000049412,0.01000,1.875
+9,self_attn.k_proj,0.0000010675,0.01000,1.881
+9,self_attn.o_proj,0.0000005296,0.01000,0.389
+9,mlp.gate_proj,0.0000204874,0.01000,1.015
+9,mlp.up_proj,0.0000196513,0.01000,1.015
+9,mlp.down_proj,0.0000019309,0.01000,2.455
+10,self_attn.q_proj,0.0000054192,0.01000,1.863
+10,self_attn.k_proj,0.0000010889,0.01000,1.877
+10,self_attn.v_proj,0.0000008506,0.01000,1.876
+10,self_attn.o_proj,0.0000007948,0.01000,0.389
+10,mlp.gate_proj,0.0000203503,0.01000,1.060
+10,mlp.up_proj,0.0000191632,0.01000,1.058
+10,mlp.down_proj,0.0000018531,0.01000,2.473
+11,self_attn.q_proj,0.0000051875,0.01000,1.921
+11,self_attn.k_proj,0.0000010387,0.01000,1.924
+11,self_attn.v_proj,0.0000006815,0.01000,1.931
+11,self_attn.o_proj,0.0000007435,0.01000,0.381
+11,mlp.gate_proj,0.0000196355,0.01000,1.046
+11,mlp.up_proj,0.0000172677,0.01000,1.052
+11,mlp.down_proj,0.0000015551,0.01000,2.454
+12,self_attn.q_proj,0.0000063423,0.01000,1.835
+12,self_attn.k_proj,0.0000013658,0.01000,1.841
+12,self_attn.v_proj,0.0000006520,0.01000,1.851
+12,self_attn.o_proj,0.0000005855,0.01000,0.382
+12,mlp.up_proj,0.0000169693,0.01000,1.050
+12,mlp.gate_proj,0.0000183821,0.01000,1.059
+12,mlp.down_proj,0.0000016567,0.01000,2.465
+13,self_attn.q_proj,0.0000038360,0.01000,1.903
+13,self_attn.k_proj,0.0000007807,0.01000,1.907
+13,self_attn.v_proj,0.0000005112,0.01000,1.913
+13,self_attn.o_proj,0.0000006059,0.01000,0.379
+13,mlp.gate_proj,0.0000169439,0.01000,1.015
+13,mlp.up_proj,0.0000162928,0.01000,1.019
+13,mlp.down_proj,0.0000014140,0.01000,2.458
+14,self_attn.q_proj,0.0000088318,0.01000,1.970
+14,self_attn.v_proj,0.0000009109,0.01000,1.981
+14,self_attn.k_proj,0.0000013579,0.01000,1.984
+14,self_attn.o_proj,0.0000005381,0.01000,0.374
+14,mlp.up_proj,0.0000184341,0.01000,1.094
+14,mlp.gate_proj,0.0000179834,0.01000,1.102
+14,mlp.down_proj,0.0000016729,0.01000,2.462
+15,self_attn.v_proj,0.0000008579,0.01000,2.009
+15,self_attn.q_proj,0.0000121671,0.01000,2.007
+15,self_attn.k_proj,0.0000009824,0.01000,2.021
+15,self_attn.o_proj,0.0000008882,0.01000,0.383
+15,mlp.up_proj,0.0000155673,0.01000,1.049
+15,mlp.gate_proj,0.0000163478,0.01000,1.055
+15,mlp.down_proj,0.0000014788,0.01000,2.486
+16,self_attn.q_proj,0.0000068865,0.01000,1.983
+16,self_attn.k_proj,0.0000013063,0.01000,1.995
+16,self_attn.v_proj,0.0000009619,0.01000,1.999
+16,self_attn.o_proj,0.0000007198,0.01000,0.387
+16,mlp.up_proj,0.0000180247,0.01000,1.104
+16,mlp.gate_proj,0.0000184467,0.01000,1.111
+16,mlp.down_proj,0.0000018679,0.01000,2.487
+17,self_attn.q_proj,0.0000067134,0.01000,2.066
+17,self_attn.v_proj,0.0000013136,0.01000,2.067
+17,self_attn.k_proj,0.0000008133,0.01000,2.070
+17,self_attn.o_proj,0.0000006762,0.01000,0.383
+17,mlp.gate_proj,0.0000189996,0.01000,1.264
+17,mlp.up_proj,0.0000189212,0.01000,1.270
+17,mlp.down_proj,0.0000023529,0.01000,2.445
+18,self_attn.q_proj,0.0000055875,0.01000,1.935
+18,self_attn.k_proj,0.0000009592,0.01000,1.948
+18,self_attn.v_proj,0.0000009516,0.01000,1.950
+18,self_attn.o_proj,0.0000009959,0.01000,0.378
+18,mlp.up_proj,0.0000208656,0.01000,1.036
+18,mlp.gate_proj,0.0000211248,0.01000,1.038
+18,mlp.down_proj,0.0000030797,0.01000,2.519
+19,self_attn.k_proj,0.0000011236,0.01000,1.900
+19,self_attn.q_proj,0.0000078805,0.01000,1.906
+19,self_attn.v_proj,0.0000018650,0.01000,1.916
+19,self_attn.o_proj,0.0000012117,0.01000,0.380
+19,mlp.gate_proj,0.0000248130,0.01000,1.022
+19,mlp.up_proj,0.0000262968,0.01000,1.026
+19,mlp.down_proj,0.0000053145,0.01000,2.447
+20,self_attn.k_proj,0.0000013334,0.01000,2.089
+20,self_attn.v_proj,0.0000025328,0.01000,2.091
+20,self_attn.q_proj,0.0000086186,0.01000,2.099
+20,self_attn.o_proj,0.0000019196,0.01000,0.382
+20,mlp.up_proj,0.0000287931,0.01000,1.094
+20,mlp.gate_proj,0.0000281793,0.01000,1.096
+20,mlp.down_proj,0.0000055514,0.01000,2.436
+21,self_attn.q_proj,0.0000090283,0.01000,1.887
+21,self_attn.v_proj,0.0000023488,0.01000,1.908
+21,self_attn.k_proj,0.0000012907,0.01000,1.912
+21,self_attn.o_proj,0.0000012837,0.01000,0.377
+21,mlp.gate_proj,0.0000403068,0.01000,1.015
+21,mlp.up_proj,0.0000402602,0.01000,1.020
+21,mlp.down_proj,0.0000089025,0.01000,2.422
+22,self_attn.q_proj,0.0000084084,0.01000,1.938
+22,self_attn.k_proj,0.0000014701,0.01000,1.951
+22,self_attn.v_proj,0.0000028296,0.01000,1.951
+22,self_attn.o_proj,0.0000017236,0.01000,0.377
+22,mlp.gate_proj,0.0000474020,0.01000,1.060
+22,mlp.up_proj,0.0000465792,0.01000,1.061
+22,mlp.down_proj,0.0000116087,0.01000,2.415
+23,self_attn.q_proj,0.0000104538,0.01000,2.275
+23,self_attn.v_proj,0.0000035433,0.01000,2.282
+23,self_attn.k_proj,0.0000016242,0.01000,2.293
+23,self_attn.o_proj,0.0000019176,0.01000,0.404
+23,mlp.up_proj,0.0000508410,0.01000,1.070
+23,mlp.gate_proj,0.0000491592,0.01000,1.079
+23,mlp.down_proj,0.0000136699,0.01000,2.446
+24,self_attn.k_proj,0.0000017392,0.01000,1.880
+24,self_attn.q_proj,0.0000107215,0.01000,1.892
+24,self_attn.v_proj,0.0000070691,0.01000,1.891
+24,self_attn.o_proj,0.0000025481,0.01000,0.376
+24,mlp.up_proj,0.0000530121,0.01000,1.051
+24,mlp.gate_proj,0.0000493621,0.01000,1.057
+24,mlp.down_proj,0.0000161085,0.01000,2.477
+25,self_attn.q_proj,0.0000103566,0.01000,2.164
+25,self_attn.v_proj,0.0000106650,0.01000,2.184
+25,self_attn.k_proj,0.0000018334,0.01000,2.193
+25,self_attn.o_proj,0.0000033180,0.01000,0.395
+25,mlp.up_proj,0.0000559266,0.01000,1.207
+25,mlp.gate_proj,0.0000488881,0.01000,1.231
+25,mlp.down_proj,0.0000200887,0.01000,2.527
+26,self_attn.q_proj,0.0000120920,0.01000,2.042
+26,self_attn.v_proj,0.0000134207,0.01000,2.060
+26,self_attn.k_proj,0.0000018492,0.01000,2.060
+26,self_attn.o_proj,0.0000024180,0.01000,0.378
+26,mlp.up_proj,0.0000555762,0.01000,1.209
+26,mlp.gate_proj,0.0000466859,0.01000,1.223
+26,mlp.down_proj,0.0000288948,0.01000,2.459
+27,self_attn.k_proj,0.0000019184,0.01000,2.009
+27,self_attn.v_proj,0.0000137570,0.01000,2.018
+27,self_attn.q_proj,0.0000120771,0.01000,2.017
+27,self_attn.o_proj,0.0000081001,0.01000,0.381
+27,mlp.up_proj,0.0000640602,0.01000,1.089
+27,mlp.gate_proj,0.0000614883,0.01000,1.090
+27,mlp.down_proj,0.0000351033,0.01000,2.442

qwen25-1p5b__gptq__openhermes__n512__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_tumiwt6x",
+    "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__s2/tokenizer.json

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

qwen25-1p5b__gptq__openhermes__n512__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
+}