Upload folder using huggingface_hub

smollm2-1p7b__gptq__openhermes__n128__s0/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-31T01:38:40.847628+00:00

smollm2-1p7b__gptq__openhermes__n128__s0/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

smollm2-1p7b__gptq__openhermes__n128__s0/config.json

@@ -0,0 +1,90 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "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_70uxcsm2",
+      "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-05,
+  "rope_parameters": {
+    "rope_theta": 130000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "5.14.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

smollm2-1p7b__gptq__openhermes__n128__s0/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.14.1"
+}

smollm2-1p7b__gptq__openhermes__n128__s0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe1a0ff2807b9c6236ac7f6c57ae94aa8e1dce770f903e768955f76168702c5
+size 1040336952

smollm2-1p7b__gptq__openhermes__n128__s0/quant_log.csv

@@ -0,0 +1,169 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000001345,0.01000,2.458
+0,self_attn.q_proj,0.0000050453,0.01000,2.464
+0,self_attn.k_proj,0.0000037300,0.01000,2.467
+0,self_attn.o_proj,0.0000001090,0.01000,0.469
+0,mlp.up_proj,0.0000045882,0.01000,1.307
+0,mlp.gate_proj,0.0000048730,0.01000,1.314
+0,mlp.down_proj,0.0000022821,0.01000,2.088
+1,self_attn.v_proj,0.0000028356,0.01000,2.484
+1,self_attn.q_proj,0.0000145915,0.01000,2.502
+1,self_attn.k_proj,0.0000125205,0.01000,2.505
+1,self_attn.o_proj,0.0000013204,0.01000,0.477
+1,mlp.up_proj,0.0000086589,0.01000,1.320
+1,mlp.gate_proj,0.0000100342,0.01000,1.328
+1,mlp.down_proj,0.0000615314,0.01000,2.102
+2,self_attn.k_proj,0.0000206162,0.01000,2.596
+2,self_attn.q_proj,0.0000235583,0.01000,2.611
+2,self_attn.v_proj,0.0000079216,0.01000,2.613
+2,self_attn.o_proj,0.0000034689,0.01000,0.476
+2,mlp.gate_proj,0.0000151693,0.01000,1.386
+2,mlp.up_proj,0.0000134773,0.01000,1.391
+2,mlp.down_proj,0.0000095484,0.01000,2.118
+3,self_attn.k_proj,0.0000275817,0.01000,2.628
+3,self_attn.q_proj,0.0000278150,0.01000,2.646
+3,self_attn.v_proj,0.0000113015,0.01000,2.647
+3,self_attn.o_proj,0.0000043517,0.01000,0.488
+3,mlp.gate_proj,0.0000183919,0.01000,1.413
+3,mlp.up_proj,0.0000174461,0.01000,1.434
+3,mlp.down_proj,0.0000154142,0.01000,2.111
+4,self_attn.v_proj,0.0000124162,0.01000,2.605
+4,self_attn.q_proj,0.0000303314,0.01000,2.617
+4,self_attn.k_proj,0.0000292143,0.01000,2.617
+4,self_attn.o_proj,0.0000069696,0.01000,0.482
+4,mlp.gate_proj,0.0000227393,0.01000,1.353
+4,mlp.up_proj,0.0000219680,0.01000,1.354
+4,mlp.down_proj,0.0000205958,0.01000,2.110
+5,self_attn.v_proj,0.0000126437,0.01000,2.627
+5,self_attn.k_proj,0.0000278638,0.01000,2.644
+5,self_attn.q_proj,0.0000291107,0.01000,2.650
+5,self_attn.o_proj,0.0000079752,0.01000,0.489
+5,mlp.gate_proj,0.0000265651,0.01000,1.483
+5,mlp.up_proj,0.0000266641,0.01000,1.493
+5,mlp.down_proj,0.0000272588,0.01000,2.101
+6,self_attn.q_proj,0.0000341684,0.01000,2.527
+6,self_attn.k_proj,0.0000316666,0.01000,2.525
+6,self_attn.v_proj,0.0000155100,0.01000,2.534
+6,self_attn.o_proj,0.0000111776,0.01000,0.478
+6,mlp.up_proj,0.0000327980,0.01000,1.391
+6,mlp.gate_proj,0.0000320942,0.01000,1.406
+6,mlp.down_proj,0.0000389394,0.01000,2.138
+7,self_attn.k_proj,0.0000344608,0.01000,2.830
+7,self_attn.v_proj,0.0000166005,0.01000,2.849
+7,self_attn.q_proj,0.0000437863,0.01000,2.857
+7,self_attn.o_proj,0.0000174155,0.01000,0.476
+7,mlp.gate_proj,0.0000390938,0.01000,1.296
+7,mlp.up_proj,0.0000416572,0.01000,1.294
+7,mlp.down_proj,0.0001193587,0.01000,2.113
+8,self_attn.v_proj,0.0000223422,0.01000,2.700
+8,self_attn.q_proj,0.0000331151,0.01000,2.714
+8,self_attn.k_proj,0.0000329468,0.01000,2.719
+8,self_attn.o_proj,0.0000360848,0.01000,0.475
+8,mlp.up_proj,0.0000478701,0.01000,1.339
+8,mlp.gate_proj,0.0000457486,0.01000,1.347
+8,mlp.down_proj,0.0000770694,0.01000,2.092
+9,self_attn.q_proj,0.0000312561,0.01000,2.636
+9,self_attn.k_proj,0.0000312051,0.01000,2.645
+9,self_attn.v_proj,0.0000198155,0.01000,2.656
+9,self_attn.o_proj,0.0000410876,0.01000,0.477
+9,mlp.up_proj,0.0000508044,0.01000,1.354
+9,mlp.gate_proj,0.0000448035,0.01000,1.359
+9,mlp.down_proj,0.0000814827,0.01000,2.091
+10,self_attn.q_proj,0.0000338167,0.01000,2.622
+10,self_attn.v_proj,0.0000202830,0.01000,2.627
+10,self_attn.k_proj,0.0000329934,0.01000,2.636
+10,self_attn.o_proj,0.0000445301,0.01000,0.474
+10,mlp.gate_proj,0.0000453390,0.01000,1.322
+10,mlp.up_proj,0.0000506058,0.01000,1.324
+10,mlp.down_proj,0.0000976274,0.01000,2.083
+11,self_attn.q_proj,0.0000343269,0.01000,2.538
+11,self_attn.k_proj,0.0000330891,0.01000,2.537
+11,self_attn.v_proj,0.0000200872,0.01000,2.549
+11,self_attn.o_proj,0.0000534225,0.01000,0.481
+11,mlp.up_proj,0.0000511555,0.01000,1.320
+11,mlp.gate_proj,0.0000461615,0.01000,1.325
+11,mlp.down_proj,0.0001067720,0.01000,2.082
+12,self_attn.q_proj,0.0000391614,0.01000,2.507
+12,self_attn.v_proj,0.0000292605,0.01000,2.510
+12,self_attn.k_proj,0.0000365343,0.01000,2.513
+12,self_attn.o_proj,0.0000735198,0.01000,0.475
+12,mlp.gate_proj,0.0000487613,0.01000,1.305
+12,mlp.up_proj,0.0000542665,0.01000,1.307
+12,mlp.down_proj,0.0001256163,0.01000,2.080
+13,self_attn.k_proj,0.0000372015,0.01000,2.519
+13,self_attn.v_proj,0.0000268166,0.01000,2.531
+13,self_attn.q_proj,0.0000392226,0.01000,2.534
+13,self_attn.o_proj,0.0000646535,0.01000,0.476
+13,mlp.gate_proj,0.0000531036,0.01000,1.299
+13,mlp.up_proj,0.0000592535,0.01000,1.305
+13,mlp.down_proj,0.0001593312,0.01000,2.070
+14,self_attn.q_proj,0.0000375656,0.01000,2.545
+14,self_attn.v_proj,0.0000296265,0.01000,2.554
+14,self_attn.k_proj,0.0000381297,0.01000,2.562
+14,self_attn.o_proj,0.0000858236,0.01000,0.473
+14,mlp.gate_proj,0.0000521157,0.01000,1.317
+14,mlp.up_proj,0.0000596621,0.01000,1.322
+14,mlp.down_proj,0.0001938178,0.01000,2.101
+15,self_attn.q_proj,0.0000418452,0.01000,2.522
+15,self_attn.v_proj,0.0000460263,0.01000,2.529
+15,self_attn.k_proj,0.0000406898,0.01000,2.533
+15,self_attn.o_proj,0.0001112366,0.01000,0.475
+15,mlp.gate_proj,0.0000583955,0.01000,1.316
+15,mlp.up_proj,0.0000679712,0.01000,1.323
+15,mlp.down_proj,0.0002954569,0.01000,2.117
+16,self_attn.k_proj,0.0000436400,0.01000,2.522
+16,self_attn.q_proj,0.0000441692,0.01000,2.525
+16,self_attn.v_proj,0.0000434791,0.01000,2.537
+16,self_attn.o_proj,0.0001430492,0.01000,0.474
+16,mlp.up_proj,0.0000865822,0.01000,1.297
+16,mlp.gate_proj,0.0000733309,0.01000,1.303
+16,mlp.down_proj,0.0004801562,0.01000,2.095
+17,self_attn.q_proj,0.0000437960,0.01000,2.585
+17,self_attn.v_proj,0.0000626271,0.01000,2.590
+17,self_attn.k_proj,0.0000435238,0.01000,2.597
+17,self_attn.o_proj,0.0002434286,0.01000,0.480
+17,mlp.gate_proj,0.0000910483,0.01000,1.365
+17,mlp.up_proj,0.0001066758,0.01000,1.370
+17,mlp.down_proj,0.0007308268,0.01000,2.095
+18,self_attn.k_proj,0.0000437945,0.01000,2.632
+18,self_attn.v_proj,0.0000741961,0.01000,2.637
+18,self_attn.q_proj,0.0000458646,0.01000,2.645
+18,self_attn.o_proj,0.0002701380,0.01000,0.478
+18,mlp.gate_proj,0.0001153555,0.01000,1.383
+18,mlp.up_proj,0.0001400817,0.01000,1.390
+18,mlp.down_proj,0.0012266923,0.01000,2.090
+19,self_attn.k_proj,0.0000470042,0.01000,2.675
+19,self_attn.q_proj,0.0000493093,0.01000,2.689
+19,self_attn.v_proj,0.0001041471,0.01000,2.689
+19,self_attn.o_proj,0.0002680051,0.01000,0.491
+19,mlp.gate_proj,0.0001325401,0.01000,1.474
+19,mlp.up_proj,0.0001662085,0.01000,1.479
+19,mlp.down_proj,0.0017112645,0.01000,2.100
+20,self_attn.q_proj,0.0000493308,0.01000,2.723
+20,self_attn.k_proj,0.0000462236,0.01000,2.731
+20,self_attn.v_proj,0.0001221305,0.01000,2.731
+20,self_attn.o_proj,0.0002966751,0.01000,0.478
+20,mlp.gate_proj,0.0001443420,0.01000,1.356
+20,mlp.up_proj,0.0001837997,0.01000,1.360
+20,mlp.down_proj,0.0020868351,0.01000,2.079
+21,self_attn.q_proj,0.0000529719,0.01000,2.641
+21,self_attn.v_proj,0.0001530800,0.01000,2.646
+21,self_attn.k_proj,0.0000512021,0.01000,2.655
+21,self_attn.o_proj,0.0004062485,0.01000,0.481
+21,mlp.gate_proj,0.0001532872,0.01000,1.357
+21,mlp.up_proj,0.0001986474,0.01000,1.367
+21,mlp.down_proj,0.0024406621,0.01000,2.105
+22,self_attn.k_proj,0.0000502429,0.01000,2.848
+22,self_attn.q_proj,0.0000526556,0.01000,2.864
+22,self_attn.v_proj,0.0001509088,0.01000,2.873
+22,self_attn.o_proj,0.0006781308,0.01000,0.493
+22,mlp.gate_proj,0.0001663718,0.01000,1.493
+22,mlp.up_proj,0.0002137939,0.01000,1.507
+22,mlp.down_proj,0.0032266029,0.01000,2.136
+23,self_attn.v_proj,0.0001907158,0.01000,2.845
+23,self_attn.k_proj,0.0000473478,0.01000,2.861
+23,self_attn.q_proj,0.0000455329,0.01000,2.870
+23,self_attn.o_proj,0.0018043798,0.01000,0.490
+23,mlp.gate_proj,0.0001869509,0.01000,1.527
+23,mlp.up_proj,0.0002253604,0.01000,1.530
+23,mlp.down_proj,0.0067221188,0.01000,2.178

smollm2-1p7b__gptq__openhermes__n128__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_70uxcsm2",
+    "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
+}

smollm2-1p7b__gptq__openhermes__n128__s0/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}