Upload config.json

config.json

@@ -4,93 +4,40 @@
   "training_timestamp": "Sat Oct 7 09:46:53 2023",
   "training_comments": "falcon-rw-1b-base",
   "_name_or_path": "tiiuae/falcon-rw-1b",
-  "model_type": "falcon",
-  "vocab_size": 50304,
-  "hidden_size": 2048,
-  "num_hidden_layers": 24,
-  "num_attention_heads": 32,
-  "layer_norm_epsilon": 1e-05,
-  "initializer_range": 0.02,
-  "use_cache": true,
-  "hidden_dropout": 0.0,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "num_kv_heads": 32,
   "alibi": true,
-  "new_decoder_architecture": false,
-  "multi_query": false,
-  "parallel_attn": false,
-  "bias": true,
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": "bfloat16",
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": true,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "cross_attention_hidden_size": null,
-  "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": null,
-  "num_return_sequences": 1,
-  "chunk_size_feed_forward": 0,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
+  "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "FalconForCausalLM"
   ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
-  "tokenizer_class": null,
-  "prefix": null,
-  "pad_token_id": null,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "tiiuae/falcon-rw-1b",
-  "transformers_version": "4.28.1",
-  "apply_residual_connection_post_layernorm": false,
+  "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_falcon.FalconConfig",
-    "AutoModel": "modeling_falcon.FalconModel",
-    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
-    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
+    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
   },
-  "trained": "custom training"
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 50304
 }
+