Upload folder using huggingface_hub

smollm2-1p7b__gptq__openhermes__n128__s1/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-31T01:45:17.644203+00:00

smollm2-1p7b__gptq__openhermes__n128__s1/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__s1/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_vvtxn0tp",
+      "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__s1/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__s1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7095dc24fda392e102c6598a4fb3ed5f66bf15883b5af932d919b8c00d08e595
+size 1040336952

smollm2-1p7b__gptq__openhermes__n128__s1/quant_log.csv

@@ -0,0 +1,169 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.0000037164,0.01000,2.618
+0,self_attn.q_proj,0.0000050321,0.01000,2.624
+0,self_attn.v_proj,0.0000001342,0.01000,2.624
+0,self_attn.o_proj,0.0000001097,0.01000,0.485
+0,mlp.gate_proj,0.0000048847,0.01000,1.408
+0,mlp.up_proj,0.0000045976,0.01000,1.411
+0,mlp.down_proj,0.0000023047,0.01000,2.159
+1,self_attn.v_proj,0.0000028583,0.01000,2.664
+1,self_attn.k_proj,0.0000126368,0.01000,2.683
+1,self_attn.q_proj,0.0000147245,0.01000,2.691
+1,self_attn.o_proj,0.0000013197,0.01000,0.491
+1,mlp.up_proj,0.0000086968,0.01000,1.346
+1,mlp.gate_proj,0.0000100810,0.01000,1.356
+1,mlp.down_proj,0.0000632180,0.01000,2.098
+2,self_attn.v_proj,0.0000079678,0.01000,2.630
+2,self_attn.k_proj,0.0000207363,0.01000,2.631
+2,self_attn.q_proj,0.0000236914,0.01000,2.633
+2,self_attn.o_proj,0.0000034619,0.01000,0.490
+2,mlp.gate_proj,0.0000153422,0.01000,1.489
+2,mlp.up_proj,0.0000136264,0.01000,1.499
+2,mlp.down_proj,0.0000098029,0.01000,2.110
+3,self_attn.q_proj,0.0000282828,0.01000,2.943
+3,self_attn.v_proj,0.0000114956,0.01000,2.981
+3,self_attn.k_proj,0.0000280416,0.01000,2.988
+3,self_attn.o_proj,0.0000043921,0.01000,0.488
+3,mlp.gate_proj,0.0000187597,0.01000,1.531
+3,mlp.up_proj,0.0000178027,0.01000,1.543
+3,mlp.down_proj,0.0000159408,0.01000,2.121
+4,self_attn.k_proj,0.0000298102,0.01000,2.647
+4,self_attn.v_proj,0.0000126463,0.01000,2.650
+4,self_attn.q_proj,0.0000309200,0.01000,2.665
+4,self_attn.o_proj,0.0000069323,0.01000,0.484
+4,mlp.gate_proj,0.0000232017,0.01000,1.502
+4,mlp.up_proj,0.0000224146,0.01000,1.508
+4,mlp.down_proj,0.0000212179,0.01000,2.108
+5,self_attn.q_proj,0.0000297079,0.01000,2.643
+5,self_attn.k_proj,0.0000283941,0.01000,2.657
+5,self_attn.v_proj,0.0000128803,0.01000,2.659
+5,self_attn.o_proj,0.0000081663,0.01000,0.480
+5,mlp.gate_proj,0.0000271369,0.01000,1.376
+5,mlp.up_proj,0.0000272436,0.01000,1.375
+5,mlp.down_proj,0.0000282903,0.01000,2.118
+6,self_attn.q_proj,0.0000348302,0.01000,2.643
+6,self_attn.k_proj,0.0000322716,0.01000,2.650
+6,self_attn.v_proj,0.0000158093,0.01000,2.654
+6,self_attn.o_proj,0.0000115479,0.01000,0.485
+6,mlp.gate_proj,0.0000327083,0.01000,1.331
+6,mlp.up_proj,0.0000334207,0.01000,1.337
+6,mlp.down_proj,0.0000401717,0.01000,2.102
+7,self_attn.q_proj,0.0000444244,0.01000,2.532
+7,self_attn.v_proj,0.0000168786,0.01000,2.542
+7,self_attn.k_proj,0.0000350099,0.01000,2.546
+7,self_attn.o_proj,0.0000177193,0.01000,0.484
+7,mlp.up_proj,0.0000424550,0.01000,1.309
+7,mlp.gate_proj,0.0000398283,0.01000,1.313
+7,mlp.down_proj,0.0001198689,0.01000,2.121
+8,self_attn.q_proj,0.0000336898,0.01000,2.905
+8,self_attn.k_proj,0.0000335314,0.01000,2.915
+8,self_attn.v_proj,0.0000227217,0.01000,2.923
+8,self_attn.o_proj,0.0000364918,0.01000,0.479
+8,mlp.up_proj,0.0000487564,0.01000,1.458
+8,mlp.gate_proj,0.0000465779,0.01000,1.466
+8,mlp.down_proj,0.0000789385,0.01000,2.110
+9,self_attn.v_proj,0.0000202139,0.01000,2.690
+9,self_attn.k_proj,0.0000317794,0.01000,2.702
+9,self_attn.q_proj,0.0000318617,0.01000,2.712
+9,self_attn.o_proj,0.0000419389,0.01000,0.491
+9,mlp.up_proj,0.0000516668,0.01000,1.342
+9,mlp.gate_proj,0.0000456286,0.01000,1.349
+9,mlp.down_proj,0.0000828304,0.01000,2.099
+10,self_attn.k_proj,0.0000335581,0.01000,2.617
+10,self_attn.q_proj,0.0000343857,0.01000,2.625
+10,self_attn.v_proj,0.0000206395,0.01000,2.632
+10,self_attn.o_proj,0.0000454655,0.01000,0.488
+10,mlp.up_proj,0.0000513614,0.01000,1.424
+10,mlp.gate_proj,0.0000460220,0.01000,1.426
+10,mlp.down_proj,0.0000990343,0.01000,2.104
+11,self_attn.q_proj,0.0000348838,0.01000,2.652
+11,self_attn.k_proj,0.0000335773,0.01000,2.661
+11,self_attn.v_proj,0.0000204059,0.01000,2.669
+11,self_attn.o_proj,0.0000543216,0.01000,0.497
+11,mlp.gate_proj,0.0000468922,0.01000,1.454
+11,mlp.up_proj,0.0000518891,0.01000,1.461
+11,mlp.down_proj,0.0001096406,0.01000,2.114
+12,self_attn.v_proj,0.0000298669,0.01000,2.622
+12,self_attn.k_proj,0.0000373066,0.01000,2.634
+12,self_attn.q_proj,0.0000400346,0.01000,2.640
+12,self_attn.o_proj,0.0000757137,0.01000,0.488
+12,mlp.up_proj,0.0000547812,0.01000,1.302
+12,mlp.gate_proj,0.0000492847,0.01000,1.310
+12,mlp.down_proj,0.0001284982,0.01000,2.081
+13,self_attn.k_proj,0.0000378295,0.01000,2.528
+13,self_attn.v_proj,0.0000272891,0.01000,2.536
+13,self_attn.q_proj,0.0000399226,0.01000,2.545
+13,self_attn.o_proj,0.0000666828,0.01000,0.479
+13,mlp.up_proj,0.0000595372,0.01000,1.413
+13,mlp.gate_proj,0.0000534080,0.01000,1.420
+13,mlp.down_proj,0.0001567927,0.01000,2.150
+14,self_attn.k_proj,0.0000383572,0.01000,3.310
+14,self_attn.v_proj,0.0000298267,0.01000,3.327
+14,self_attn.q_proj,0.0000377720,0.01000,3.346
+14,self_attn.o_proj,0.0000843472,0.01000,0.506
+14,mlp.gate_proj,0.0000524255,0.01000,1.401
+14,mlp.up_proj,0.0000600146,0.01000,1.406
+14,mlp.down_proj,0.0001928546,0.01000,2.081
+15,self_attn.q_proj,0.0000420181,0.01000,2.553
+15,self_attn.v_proj,0.0000463451,0.01000,2.556
+15,self_attn.k_proj,0.0000409804,0.01000,2.571
+15,self_attn.o_proj,0.0001121817,0.01000,0.477
+15,mlp.gate_proj,0.0000589028,0.01000,1.294
+15,mlp.up_proj,0.0000684685,0.01000,1.294
+15,mlp.down_proj,0.0003007465,0.01000,2.098
+16,self_attn.k_proj,0.0000439381,0.01000,2.534
+16,self_attn.v_proj,0.0000438044,0.01000,2.549
+16,self_attn.q_proj,0.0000443802,0.01000,2.561
+16,self_attn.o_proj,0.0001424637,0.01000,0.471
+16,mlp.gate_proj,0.0000736872,0.01000,1.400
+16,mlp.up_proj,0.0000868651,0.01000,1.417
+16,mlp.down_proj,0.0004843921,0.01000,2.124
+17,self_attn.v_proj,0.0000632349,0.01000,2.779
+17,self_attn.q_proj,0.0000442260,0.01000,2.788
+17,self_attn.k_proj,0.0000439361,0.01000,2.799
+17,self_attn.o_proj,0.0002391510,0.01000,0.496
+17,mlp.up_proj,0.0001077866,0.01000,1.400
+17,mlp.gate_proj,0.0000920379,0.01000,1.408
+17,mlp.down_proj,0.0007436379,0.01000,2.137
+18,self_attn.k_proj,0.0000444351,0.01000,2.675
+18,self_attn.v_proj,0.0000751335,0.01000,2.691
+18,self_attn.q_proj,0.0000464369,0.01000,2.687
+18,self_attn.o_proj,0.0002742518,0.01000,0.496
+18,mlp.gate_proj,0.0001166276,0.01000,1.392
+18,mlp.up_proj,0.0001415495,0.01000,1.401
+18,mlp.down_proj,0.0012448951,0.01000,2.128
+19,self_attn.k_proj,0.0000475584,0.01000,2.670
+19,self_attn.q_proj,0.0000498442,0.01000,2.680
+19,self_attn.v_proj,0.0001054401,0.01000,2.690
+19,self_attn.o_proj,0.0002733438,0.01000,0.490
+19,mlp.gate_proj,0.0001336894,0.01000,1.414
+19,mlp.up_proj,0.0001677261,0.01000,1.428
+19,mlp.down_proj,0.0017324619,0.01000,2.131
+20,self_attn.q_proj,0.0000497656,0.01000,2.766
+20,self_attn.k_proj,0.0000466720,0.01000,2.770
+20,self_attn.v_proj,0.0001233979,0.01000,2.777
+20,self_attn.o_proj,0.0003004726,0.01000,0.491
+20,mlp.up_proj,0.0001850390,0.01000,1.446
+20,mlp.gate_proj,0.0001453950,0.01000,1.458
+20,mlp.down_proj,0.0021149018,0.01000,2.138
+21,self_attn.v_proj,0.0001539769,0.01000,2.711
+21,self_attn.k_proj,0.0000513852,0.01000,2.729
+21,self_attn.q_proj,0.0000533995,0.01000,2.737
+21,self_attn.o_proj,0.0003996050,0.01000,0.491
+21,mlp.gate_proj,0.0001555253,0.01000,1.400
+21,mlp.up_proj,0.0002015242,0.01000,1.406
+21,mlp.down_proj,0.0025056920,0.01000,2.131
+22,self_attn.v_proj,0.0001523640,0.01000,2.645
+22,self_attn.q_proj,0.0000531464,0.01000,2.655
+22,self_attn.k_proj,0.0000507017,0.01000,2.662
+22,self_attn.o_proj,0.0006854037,0.01000,0.484
+22,mlp.gate_proj,0.0001683898,0.01000,1.391
+22,mlp.up_proj,0.0002164323,0.01000,1.396
+22,mlp.down_proj,0.0033443385,0.01000,2.143
+23,self_attn.q_proj,0.0000459398,0.01000,2.770
+23,self_attn.v_proj,0.0001920842,0.01000,2.797
+23,self_attn.k_proj,0.0000478304,0.01000,2.802
+23,self_attn.o_proj,0.0019371900,0.01000,0.500
+23,mlp.gate_proj,0.0001891020,0.01000,1.399
+23,mlp.up_proj,0.0002280652,0.01000,1.405
+23,mlp.down_proj,0.0069962386,0.01000,2.122

smollm2-1p7b__gptq__openhermes__n128__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_vvtxn0tp",
+    "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__s1/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
+}