Update config.json

config.json

@@ -1,99 +1,44 @@
 {
-    "vocab_size": 65024,
-    "hidden_size": 4544,
-    "n_layer": 32,
-    "n_head": 71,
-    "layer_norm_epsilon": "1e-05",
-    "initializer_range": 0.02,
-    "use_cache": false,
-    "apply_residual_connection_post_layernorm": false,
-    "hidden_dropout": 0.0,
-    "attention_dropout": 0.0,
-    "bos_token_id": 11,
-    "eos_token_id": 11,
-    "multi_query": true,
-    "alibi": false,
-    "bias": false,
-    "parallel_attn": 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": "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,
-    "chunk_size_feed_forward": 0,
-    "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": [
-        "RWForCausalLM"
-    ],
-    "finetuning_task": "None",
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
-    "tokenizer_class": "None",
-    "prefix": "None",
-    "pad_token_id": "None",
-    "sep_token_id": "None",
-    "decoder_start_token_id": "None",
-    "task_specific_params": "None",
-    "problem_type": "None",
-    "_name_or_path": "tiiuae/falcon-7b",
-    "transformers_version": "4.31.0",
-    "auto_map": {
-        "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
-        "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
-        "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
-        "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification",
-        "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
-        "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM"
-    },
-    "model_type": "RefinedWebModel",
-    "quantization_config": {
-        "load_in_8bit": false,
-        "load_in_4bit": true,
-        "llm_int8_threshold": 6.0,
-        "llm_int8_skip_modules": "None",
-        "llm_int8_enable_fp32_cpu_offload": false,
-        "llm_int8_has_fp16_weight": false,
-        "bnb_4bit_quant_type": "nf4",
-        "bnb_4bit_use_double_quant": false,
-        "bnb_4bit_compute_dtype": "float16"
-    }
+  "_name_or_path": "tiiuae/falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 65024
 }