Ajout OSCAR 100G

cam_run30/model_info.txt

@@ -0,0 +1,90 @@
+=== Dataset Information ===
+Total tokens: 26,843,545,600
+Estimated size: 100.00 GB
+
+=== Model Architecture ===
+return_dict: True
+output_hidden_states: False
+output_attentions: False
+torchscript: False
+torch_dtype: float32
+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: ['RobertaForMaskedLM']
+finetuning_task: None
+id2label: {0: 'LABEL_0', 1: 'LABEL_1'}
+label2id: {'LABEL_0': 0, 'LABEL_1': 1}
+tokenizer_class: None
+prefix: None
+bos_token_id: 0
+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: 
+_attn_implementation_autoset: False
+transformers_version: 4.46.3
+vocab_size: 50265
+hidden_size: 768
+num_hidden_layers: 12
+num_attention_heads: 12
+hidden_act: gelu
+intermediate_size: 3072
+hidden_dropout_prob: 0.1
+attention_probs_dropout_prob: 0.1
+max_position_embeddings: 514
+type_vocab_size: 1
+initializer_range: 0.02
+layer_norm_eps: 1e-05
+position_embedding_type: absolute
+use_cache: True
+classifier_dropout: None
+model_type: roberta
+
+=== Training Parameters ===
+learning_rate: 0.0007
+batch_size: 64
+gradient_accumulation: 5
+warmup_steps: 10000
+total_steps: 100000
+
+=== Dataset Configuration ===
+Dataset: oscar-corpus/OSCAR-2301
+Subset: fr
+Split: train
+Streaming: True

cam_run30/weights/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run30/weights/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde2920dde116000e56b077c7f4b1f567967425441e1b3993fea0fe2b8f2328b
+size 498813948

cam_run30/weights/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

cam_run30/weights/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}