Upload Eagle3 checkpoint (epoch-0-step-5000)

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      11,
+      21
+    ]
+  },
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initializer_range": 0.02,
+  "intermediate_size": 17280,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 201088
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e876191fc05f682deb8182f21423b5aaad702d6e36099611f8910258523d713
+size 615741792

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bf4fde04d5092bd08690c8f7a5105e13a7af2e0128eb7a6bfcd47f3ad1bd0a
+size 4439