Upload folder using huggingface_hub

smollm2-1p7b__gptq__openhermes__n128__s2/BENCH_DONE

@@ -0,0 +1 @@
+2026-07-31T01:52:02.967008+00:00

smollm2-1p7b__gptq__openhermes__n128__s2/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__s2/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_qtiao63a",
+      "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__s2/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__s2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa9da18ab0ff4bfd909b85b5adc93f1f3989bc8b6094cbdbf697dea613a74f
+size 1040336952

smollm2-1p7b__gptq__openhermes__n128__s2/quant_log.csv

@@ -0,0 +1,169 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.0000038255,0.01000,2.863
+0,self_attn.v_proj,0.0000001375,0.01000,2.884
+0,self_attn.q_proj,0.0000051801,0.01000,2.896
+0,self_attn.o_proj,0.0000001121,0.01000,0.498
+0,mlp.gate_proj,0.0000050386,0.01000,1.547
+0,mlp.up_proj,0.0000047440,0.01000,1.555
+0,mlp.down_proj,0.0000023878,0.01000,2.171
+1,self_attn.v_proj,0.0000029343,0.01000,2.884
+1,self_attn.q_proj,0.0000150696,0.01000,2.892
+1,self_attn.k_proj,0.0000129598,0.01000,2.905
+1,self_attn.o_proj,0.0000013488,0.01000,0.502
+1,mlp.gate_proj,0.0000104067,0.01000,1.547
+1,mlp.up_proj,0.0000089825,0.01000,1.573
+1,mlp.down_proj,0.0000562514,0.01000,2.166
+2,self_attn.v_proj,0.0000081997,0.01000,2.972
+2,self_attn.q_proj,0.0000244573,0.01000,2.997
+2,self_attn.k_proj,0.0000213623,0.01000,3.003
+2,self_attn.o_proj,0.0000035696,0.01000,0.520
+2,mlp.gate_proj,0.0000157260,0.01000,1.545
+2,mlp.up_proj,0.0000139735,0.01000,1.559
+2,mlp.down_proj,0.0000101184,0.01000,2.180
+3,self_attn.k_proj,0.0000286779,0.01000,2.950
+3,self_attn.q_proj,0.0000288668,0.01000,2.965
+3,self_attn.v_proj,0.0000117237,0.01000,2.968
+3,self_attn.o_proj,0.0000045832,0.01000,0.505
+3,mlp.up_proj,0.0000180069,0.01000,1.627
+3,mlp.gate_proj,0.0000189961,0.01000,1.640
+3,mlp.down_proj,0.0000162250,0.01000,2.154
+4,self_attn.q_proj,0.0000315570,0.01000,2.913
+4,self_attn.v_proj,0.0000128859,0.01000,2.943
+4,self_attn.k_proj,0.0000304087,0.01000,2.952
+4,self_attn.o_proj,0.0000068564,0.01000,0.501
+4,mlp.up_proj,0.0000229229,0.01000,1.563
+4,mlp.gate_proj,0.0000237380,0.01000,1.640
+4,mlp.down_proj,0.0000216042,0.01000,2.197
+5,self_attn.v_proj,0.0000130814,0.01000,2.915
+5,self_attn.q_proj,0.0000302023,0.01000,2.941
+5,self_attn.k_proj,0.0000288424,0.01000,2.945
+5,self_attn.o_proj,0.0000081751,0.01000,0.490
+5,mlp.gate_proj,0.0000274757,0.01000,1.565
+5,mlp.up_proj,0.0000275837,0.01000,1.582
+5,mlp.down_proj,0.0000285770,0.01000,2.158
+6,self_attn.q_proj,0.0000352731,0.01000,2.920
+6,self_attn.k_proj,0.0000327153,0.01000,2.938
+6,self_attn.v_proj,0.0000159867,0.01000,2.941
+6,self_attn.o_proj,0.0000111927,0.01000,0.493
+6,mlp.gate_proj,0.0000331600,0.01000,1.580
+6,mlp.up_proj,0.0000338860,0.01000,1.592
+6,mlp.down_proj,0.0000408965,0.01000,2.179
+7,self_attn.v_proj,0.0000170997,0.01000,2.891
+7,self_attn.k_proj,0.0000355364,0.01000,2.907
+7,self_attn.q_proj,0.0000449865,0.01000,2.917
+7,self_attn.o_proj,0.0000171265,0.01000,0.525
+7,mlp.gate_proj,0.0000406929,0.01000,1.561
+7,mlp.up_proj,0.0000433146,0.01000,1.575
+7,mlp.down_proj,0.0001215720,0.01000,2.154
+8,self_attn.q_proj,0.0000342925,0.01000,2.967
+8,self_attn.k_proj,0.0000341732,0.01000,2.985
+8,self_attn.v_proj,0.0000231667,0.01000,2.996
+8,self_attn.o_proj,0.0000370323,0.01000,0.510
+8,mlp.up_proj,0.0000496479,0.01000,1.575
+8,mlp.gate_proj,0.0000474595,0.01000,1.597
+8,mlp.down_proj,0.0000811481,0.01000,2.183
+9,self_attn.v_proj,0.0000205899,0.01000,3.228
+9,self_attn.k_proj,0.0000324541,0.01000,3.243
+9,self_attn.q_proj,0.0000325104,0.01000,3.250
+9,self_attn.o_proj,0.0000426773,0.01000,0.575
+9,mlp.gate_proj,0.0000464066,0.01000,1.562
+9,mlp.up_proj,0.0000525804,0.01000,1.595
+9,mlp.down_proj,0.0000843251,0.01000,2.216
+10,self_attn.k_proj,0.0000341981,0.01000,2.796
+10,self_attn.v_proj,0.0000210066,0.01000,2.798
+10,self_attn.q_proj,0.0000350746,0.01000,2.811
+10,self_attn.o_proj,0.0000463417,0.01000,0.492
+10,mlp.gate_proj,0.0000468475,0.01000,1.644
+10,mlp.up_proj,0.0000522386,0.01000,1.668
+10,mlp.down_proj,0.0001012705,0.01000,2.103
+11,self_attn.q_proj,0.0000355893,0.01000,2.569
+11,self_attn.v_proj,0.0000208092,0.01000,2.577
+11,self_attn.k_proj,0.0000342783,0.01000,2.583
+11,self_attn.o_proj,0.0000552706,0.01000,0.477
+11,mlp.up_proj,0.0000526114,0.01000,1.418
+11,mlp.gate_proj,0.0000475115,0.01000,1.426
+11,mlp.down_proj,0.0001112169,0.01000,2.068
+12,self_attn.k_proj,0.0000378375,0.01000,2.555
+12,self_attn.q_proj,0.0000405527,0.01000,2.573
+12,self_attn.v_proj,0.0000303059,0.01000,2.572
+12,self_attn.o_proj,0.0000766988,0.01000,0.473
+12,mlp.up_proj,0.0000553222,0.01000,1.353
+12,mlp.gate_proj,0.0000497843,0.01000,1.361
+12,mlp.down_proj,0.0001289696,0.01000,2.067
+13,self_attn.q_proj,0.0000403881,0.01000,2.500
+13,self_attn.k_proj,0.0000382762,0.01000,2.511
+13,self_attn.v_proj,0.0000275343,0.01000,2.516
+13,self_attn.o_proj,0.0000672205,0.01000,0.473
+13,mlp.up_proj,0.0000598844,0.01000,1.312
+13,mlp.gate_proj,0.0000537033,0.01000,1.319
+13,mlp.down_proj,0.0001572023,0.01000,2.078
+14,self_attn.k_proj,0.0000388326,0.01000,2.591
+14,self_attn.v_proj,0.0000301860,0.01000,2.590
+14,self_attn.q_proj,0.0000383174,0.01000,2.601
+14,self_attn.o_proj,0.0000869156,0.01000,0.472
+14,mlp.gate_proj,0.0000525807,0.01000,1.311
+14,mlp.up_proj,0.0000602038,0.01000,1.313
+14,mlp.down_proj,0.0001939226,0.01000,2.101
+15,self_attn.k_proj,0.0000414550,0.01000,2.660
+15,self_attn.q_proj,0.0000425911,0.01000,2.668
+15,self_attn.v_proj,0.0000468495,0.01000,2.665
+15,self_attn.o_proj,0.0001152480,0.01000,0.481
+15,mlp.up_proj,0.0000691084,0.01000,1.366
+15,mlp.gate_proj,0.0000594194,0.01000,1.368
+15,mlp.down_proj,0.0003036604,0.01000,2.090
+16,self_attn.q_proj,0.0000449496,0.01000,2.572
+16,self_attn.k_proj,0.0000446115,0.01000,2.575
+16,self_attn.v_proj,0.0000443705,0.01000,2.576
+16,self_attn.o_proj,0.0001427957,0.01000,0.475
+16,mlp.gate_proj,0.0000741048,0.01000,1.332
+16,mlp.up_proj,0.0000873281,0.01000,1.336
+16,mlp.down_proj,0.0004847311,0.01000,2.093
+17,self_attn.v_proj,0.0000638102,0.01000,2.649
+17,self_attn.k_proj,0.0000443492,0.01000,2.652
+17,self_attn.q_proj,0.0000444739,0.01000,2.656
+17,self_attn.o_proj,0.0002395073,0.01000,0.486
+17,mlp.up_proj,0.0001088830,0.01000,1.477
+17,mlp.gate_proj,0.0000930416,0.01000,1.484
+17,mlp.down_proj,0.0007601399,0.01000,2.090
+18,self_attn.q_proj,0.0000471465,0.01000,2.541
+18,self_attn.k_proj,0.0000451316,0.01000,2.540
+18,self_attn.v_proj,0.0000763045,0.01000,2.554
+18,self_attn.o_proj,0.0002772804,0.01000,0.476
+18,mlp.gate_proj,0.0001175402,0.01000,1.353
+18,mlp.up_proj,0.0001426314,0.01000,1.358
+18,mlp.down_proj,0.0012681967,0.01000,2.067
+19,self_attn.q_proj,0.0000505986,0.01000,2.589
+19,self_attn.k_proj,0.0000484454,0.01000,2.592
+19,self_attn.v_proj,0.0001071391,0.01000,2.603
+19,self_attn.o_proj,0.0002752909,0.01000,0.470
+19,mlp.up_proj,0.0001694352,0.01000,1.291
+19,mlp.gate_proj,0.0001352146,0.01000,1.297
+19,mlp.down_proj,0.0017688940,0.01000,2.072
+20,self_attn.v_proj,0.0001256965,0.01000,2.757
+20,self_attn.k_proj,0.0000475424,0.01000,2.760
+20,self_attn.q_proj,0.0000506509,0.01000,2.784
+20,self_attn.o_proj,0.0003036487,0.01000,0.474
+20,mlp.gate_proj,0.0001468516,0.01000,1.400
+20,mlp.up_proj,0.0001869773,0.01000,1.400
+20,mlp.down_proj,0.0021530311,0.01000,2.061
+21,self_attn.q_proj,0.0000543768,0.01000,2.495
+21,self_attn.v_proj,0.0001570273,0.01000,2.497
+21,self_attn.k_proj,0.0000525388,0.01000,2.501
+21,self_attn.o_proj,0.0004084973,0.01000,0.469
+21,mlp.gate_proj,0.0001570595,0.01000,1.282
+21,mlp.up_proj,0.0002036701,0.01000,1.286
+21,mlp.down_proj,0.0025507547,0.01000,2.076
+22,self_attn.q_proj,0.0000543266,0.01000,2.505
+22,self_attn.k_proj,0.0000518289,0.01000,2.520
+22,self_attn.v_proj,0.0001554941,0.01000,2.527
+22,self_attn.o_proj,0.0007020080,0.01000,0.473
+22,mlp.gate_proj,0.0001711530,0.01000,1.360
+22,mlp.up_proj,0.0002201551,0.01000,1.365
+22,mlp.down_proj,0.0033790364,0.01000,2.064
+23,self_attn.q_proj,0.0000469498,0.01000,2.524
+23,self_attn.v_proj,0.0001963330,0.01000,2.528
+23,self_attn.k_proj,0.0000488913,0.01000,2.537
+23,self_attn.o_proj,0.0018208771,0.01000,0.471
+23,mlp.up_proj,0.0002315692,0.01000,1.384
+23,mlp.gate_proj,0.0001919958,0.01000,1.386
+23,mlp.down_proj,0.0071441582,0.01000,2.066

smollm2-1p7b__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_qtiao63a",
+    "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__s2/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
+}