Upload folder using huggingface_hub

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "GptOssForCausalLMEagle3"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      11,
+      21
+    ]
+  },
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initializer_range": 0.02,
+  "intermediate_size": 17280,
+  "layer_types": [
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "num_local_experts": 16,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000.0,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "vocab_size": 201088
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec05fe46c6dde50699746a69d26383291f65447dfaaf47560be7d8b712b626e2
+size 4911688320

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6636effe04d4fa14e25513b80854a7f5da30d2a058235107b4b8c50c55871f2d
+size 184320128

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a11f7addfb1370884d8318a1bddf1639411c53b03cba218b9aef85a71dbbc2b
+size 1511859904

model.safetensors.index.json

@@ -0,0 +1,26 @@
+{
+  "metadata": {
+    "total_parameters": 390863522,
+    "total_size": 5096006560
+  },
+  "weight_map": {
+    "d2t": "model-00001-of-00002.safetensors",
+    "fc.weight": "model-00001-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "midlayer.hidden_norm.weight": "model-00001-of-00002.safetensors",
+    "midlayer.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.router.bias": "model-00001-of-00002.safetensors",
+    "midlayer.mlp.router.weight": "model-00001-of-00002.safetensors",
+    "midlayer.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "midlayer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "midlayer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "midlayer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "midlayer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00001-of-00002.safetensors",
+    "t2d": "model-00001-of-00002.safetensors"
+  }
+}

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51276b98aaba28b36e4f47f845e0ac7f34e4a94b49b8dc68cd76335c5386c8b0
+size 4567