Upload DFlash draft model for Alpamayo1.5 10B speculative decoding

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "DFlashDraftModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "block_size": 8,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
+  "mask_token_id": 155697,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 2,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_target_layers": 36,
+  "resolution_scale": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "target_layer_ids": [
+    24,
+    30,
+    31,
+    32,
+    34
+  ],
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 155697
+}

mask_embedding.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2489e4a6a32013a5dcb9f5eddf6f0f492aadd3c40e0d04348528964ba0b265af
+size 9818

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8616581ab2184e04b2fd91c2229b7ae0845ced45207b46bbed76f30077c8d509
+size 939576920

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6d29e97649598b6f6b04f0630eb85bd405367a40737993af7ea7c9babc2429
+size 1879170873