Copy from source_repo

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "draft_vocab_size": 32000,
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      17,
+      33
+    ]
+  },
+  "eos_token_id": 200002,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "pad_token_id": 199999,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 150000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 201088
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1ed4c9b6a86b6dd908f21bb2f1b667b1c61327254d33f1fb23cbfa9617c9ea
+size 1770322408

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83209f10a7135969dc833d0e7c3c811d7f21ed30cd932575837cda4e6264e430
+size 9175