Upload folder using huggingface_hub

iter_0020001_hf_bf16/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 163584,
+  "draft_vocab_size": 163840,
+  "dtype": "float32",
+  "eos_token_id": 163585,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 64,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 163840
+}

iter_0020001_hf_bf16/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf28f45e562c558c2f820ca9bd3e1b3070ac6e9cf7db8f66f08117c8e12e07f1
+size 2348810344

iter_0020001_hf_bf16/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a76257f920b6c5ec089ea4d2bbcb224127d8bba233f51b02af5d170f5ec4587
+size 1658905832

iter_0020001_hf_bf16/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750794bbfaecc773c3f6bf66e877aec0b5a79b3977032313083773fa87b236e4
+size 2348810336

iter_0020001_hf_bf16/model.safetensors.index.json

@@ -0,0 +1,22 @@
+{
+  "metadata": {
+    "total_parameters": 3178262528,
+    "total_size": 12713050112
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "fc.weight": "model-00002-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "midlayer.hidden_norm.weight": "model-00002-of-00003.safetensors",
+    "midlayer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "midlayer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "midlayer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "midlayer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "norm.weight": "model-00002-of-00003.safetensors"
+  }
+}