Upload folder using huggingface_hub

config.json

@@ -17,19 +17,12 @@
       "name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
       "architectures": [
         "LlamaForCausalLM"
-      ],
-      "hidden_size": 4096,
-      "intermediate_size": 14336,
-      "vocab_size": 128256,
-      "max_position_embeddings": 2048,
-      "bos_token_id": 128000,
-      "eos_token_id": [
-        128001
       ]
     }
   },
   "architectures": [
-    "EagleSpeculator"
+    "EagleSpeculator",
+    "LlamaDecoderLayer"
   ],
   "transformer_layer_architecture": "LlamaDecoderLayer",
   "transformer_layer_config": {
@@ -51,72 +44,73 @@
     "attention_dropout": 0.0,
     "mlp_bias": false,
     "head_dim": 128,
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": null,
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
     "tie_word_embeddings": false,
-    "chunk_size_feed_forward": 0,
-    "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,
-    "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,
-    "architectures": null,
-    "finetuning_task": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "tokenizer_class": null,
-    "prefix": null,
     "bos_token_id": 128000,
     "pad_token_id": 0,
     "eos_token_id": 128001,
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "",
     "transformers_version": "4.52.4",
     "model_type": "llama"
   },
   "layernorms": false,
   "fusion_bias": false,
   "_name_or_path": "",
-  "model_type": "speculator_model",
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.52.4",
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "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": 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,
+  "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,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": null,
+  "eos_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b25efb464e49b01c3984363116b1b8f546324de692f5f588f4d0efe1f2bdee
-size 1553998888
+oid sha256:adbcdcf98c9a8f53220e9026425d252a35f16f55a210359764c8c0665077855c
+size 503325648