Upload folder using huggingface_hub (#2)

- 1908e225640895305f2166e92906b76cb5e1577d35c2096ec0fb015450d2a60c (5a124f50e12ef75bd986ba36489193aa8ed541bd)

config.json

@@ -24,7 +24,7 @@
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float16",
-  "transformers_version": "4.37.1",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 50272,
   "word_embed_proj_dim": 768

results.json

@@ -0,0 +1,34 @@
+{
+    "base_current_gpu_type": "NVIDIA A100-PCIE-40GB",
+    "base_current_gpu_total_memory": 40339.3125,
+    "base_memory_inference_first": 690.0,
+    "base_memory_inference": 570.0,
+    "base_token_generation_latency_sync": 25.232858657836914,
+    "base_token_generation_latency_async": 25.168074667453766,
+    "base_token_generation_throughput_sync": 0.03963086440423651,
+    "base_token_generation_throughput_async": 0.03973287640048031,
+    "base_token_generation_CO2_emissions": 6.916667409165086e-06,
+    "base_token_generation_energy_consumption": 0.001975681904854854,
+    "base_inference_latency_sync": 25.73680648803711,
+    "base_inference_latency_async": 25.754165649414062,
+    "base_inference_throughput_sync": 0.03885485949722692,
+    "base_inference_throughput_async": 0.03882867003391939,
+    "base_inference_CO2_emissions": 8.20508156037289e-06,
+    "base_inference_energy_consumption": 1.885578995579329e-05,
+    "smashed_current_gpu_type": "NVIDIA A100-PCIE-40GB",
+    "smashed_current_gpu_total_memory": 40339.3125,
+    "smashed_memory_inference_first": 104.0,
+    "smashed_memory_inference": 106.0,
+    "smashed_token_generation_latency_sync": 53.81842727661133,
+    "smashed_token_generation_latency_async": 53.83266881108284,
+    "smashed_token_generation_throughput_sync": 0.01858099633533113,
+    "smashed_token_generation_throughput_async": 0.018576080697565642,
+    "smashed_token_generation_CO2_emissions": 1.4030177588319765e-05,
+    "smashed_token_generation_energy_consumption": 0.004235501136593081,
+    "smashed_inference_latency_sync": 53.602509307861325,
+    "smashed_inference_latency_async": 53.591203689575195,
+    "smashed_inference_throughput_sync": 0.018655843036313607,
+    "smashed_inference_throughput_async": 0.018659778679211203,
+    "smashed_inference_CO2_emissions": 1.382929576343033e-05,
+    "smashed_inference_energy_consumption": 3.627959529056468e-05
+}

smash_config.json

@@ -2,23 +2,23 @@
     "api_key": null,
     "verify_url": "http://johnrachwan.pythonanywhere.com",
     "smash_config": {
-        "pruners": "None",
+        "pruners": "[]",
         "pruning_ratio": 0.0,
-        "factorizers": "None",
+        "factorizers": "[]",
         "quantizers": "['hqq']",
         "weight_quantization_bits": 2,
-        "output_deviation": 0.005,
-        "compilers": "None",
+        "output_deviation": 0.01,
+        "compilers": "[]",
         "static_batch": true,
         "static_shape": true,
         "controlnet": "None",
         "unet_dim": 4,
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models3n5qn6pr",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsmj5uzwwc",
         "batch_size": 1,
         "tokenizer": "GPT2TokenizerFast(name_or_path='facebook/opt-125m', vocab_size=50265, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '</s>', 'eos_token': '</s>', 'unk_token': '</s>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={\n\t1: AddedToken(\"<pad>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n\t2: AddedToken(\"</s>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n}",
         "task": "text_text_generation",
-        "model_config": "{'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['OPTForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': '</s>', 'bos_token_id': 2, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/opt-125m', 'transformers_version': '4.37.1', 'activation_dropout': 0.0, 'model_type': 'opt', 'vocab_size': 50272, 'max_position_embeddings': 2048, 'num_attention_heads': 12, 'word_embed_proj_dim': 768, 'ffn_dim': 3072, 'hidden_size': 768, 'num_hidden_layers': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'layerdrop': 0.0, 'use_cache': True, 'do_layer_norm_before': True, 'enable_bias': True, 'layer_norm_elementwise_affine': True, '_remove_final_layer_norm': False}",
+        "model_config": "{'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['OPTForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': '</s>', 'bos_token_id': 2, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/opt-125m', 'transformers_version': '4.40.0', 'activation_dropout': 0.0, 'model_type': 'opt', 'vocab_size': 50272, 'max_position_embeddings': 2048, 'num_attention_heads': 12, 'word_embed_proj_dim': 768, 'ffn_dim': 3072, 'hidden_size': 768, 'num_hidden_layers': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_function': 'relu', 'init_std': 0.02, 'layerdrop': 0.0, 'use_cache': True, 'do_layer_norm_before': True, 'enable_bias': True, 'layer_norm_elementwise_affine': True, '_remove_final_layer_norm': False}",
         "model_name": "facebook/opt-125m",
         "max_batch_size": 1,
         "qtype_weight": "torch.qint8",