Update config.json

config.json

@@ -1,85 +1,85 @@
 {
-"add_cross_attention": false,
-"architectures": [
-"LlamaForCausalLM"
-],
-"attention_bias": false,
-"attention_dropout": 0,
-"bad_words_ids": null,
-"begin_suppress_tokens": null,
-"bos_token_id": 128000,
-"chunk_size_feed_forward": 0,
-"cross_attention_hidden_size": null,
-"decoder_start_token_id": null,
-"diversity_penalty": 0,
-"do_sample": false,
-"early_stopping": false,
-"encoder_no_repeat_ngram_size": 0,
-"eos_token_id": 128001,
-"exponential_decay_length_penalty": null,
-"finetuning_task": null,
-"forced_bos_token_id": null,
-"forced_eos_token_id": null,
-"hidden_act": "silu",
-"hidden_size": 4096,
-"id2label": {
-"0": "LABEL_0",
-"1": "LABEL_1"
-},
-"initializer_range": 0.02,
-"intermediate_size": 14336,
-"is_decoder": false,
-"is_encoder_decoder": false,
-"label2id": {
-"LABEL_0": 0,
-"LABEL_1": 1
-},
-"length_penalty": 1,
-"max_length": 20,
-"max_position_embeddings": 8192,
-"min_length": 0,
-"model_type": "llama",
-"no_repeat_ngram_size": 0,
-"num_attention_heads": 32,
-"num_beam_groups": 1,
-"num_beams": 1,
-"num_hidden_layers": 32,
-"num_key_value_heads": 8,
-"num_return_sequences": 1,
-"output_attentions": false,
-"output_hidden_states": false,
-"output_scores": false,
-"pad_token_id": null,
-"prefix": null,
-"pretraining_tp": 1,
-"problem_type": null,
-"pruned_heads": {},
-"quantization": {
-"group_size": 64,
-"bits": 4
-},
-"remove_invalid_values": false,
-"repetition_penalty": 1,
-"return_dict": true,
-"return_dict_in_generate": false,
-"rms_norm_eps": 0.00001,
-"rope_scaling": null,
-"rope_theta": 500000,
-"sep_token_id": null,
-"suppress_tokens": null,
-"task_specific_params": null,
-"temperature": 1,
-"tf_legacy_loss": false,
-"tie_encoder_decoder": false,
-"tie_word_embeddings": false,
-"tokenizer_class": null,
-"top_k": 50,
-"top_p": 1,
-"torch_dtype": "bfloat16",
-"torchscript": false,
-"transformers_version": "4.40.0",
-"typical_p": 1,
-"use_bfloat16": false,
-"use_cache": true,
-"vocab_size": 128256
+    "add_cross_attention": false,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 128001,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 8192,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.40.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128256
 }