Add files using upload-large-folder tool

dflash-7b-draft/config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "DFlashDraftModel"
+  ],
+  "model_type": "qwen3",
+  "hidden_size": 4096,
+  "intermediate_size": 11008,
+  "num_hidden_layers": 8,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "attention_bias": false,
+  "vocab_size": 129280,
+  "max_position_embeddings": 65536,
+  "rope_theta": 500000,
+  "rope_scaling": null,
+  "sliding_window": 128,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "block_size": 11,
+  "num_target_layers": 32,
+  "torch_dtype": "bfloat16",
+  "tie_word_embeddings": false,
+  "dflash_config": {
+    "mask_token_id": 128000,
+    "target_layer_ids": [
+      1,
+      5,
+      9,
+      13,
+      17,
+      21,
+      25,
+      29
+    ],
+    "num_target_layers": 32,
+    "block_size": 11,
+    "use_attention_sink": true,
+    "sliding_window": 128
+  }
+}

dflash-7b-draft/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9743c058a5cec811bc23a9f96a28792c602bcdc3618257a26223f4a45ba0cb
+size 1157692464

dflash-7b-draft/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0fa8fd2c61f44446c24a500ab64222dc64596c3408b473c3f99e61cb7992ed
+size 1195487976

dflash-7b-draft/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7e0d50e605bfe099243b5281a9ff6c8666167ea06fb95cfc98d547cdab66c5
+size 750853312

dflash-7b-draft/model.safetensors.index.json

@@ -0,0 +1,107 @@
+{
+  "metadata": {
+    "total_size": 3104023040
+  },
+  "weight_map": {
+    "fc.weight": "model-00001-of-00003.safetensors",
+    "hidden_norm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.sinks": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.sinks": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.2.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.sinks": "model-00002-of-00003.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.3.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.sinks": "model-00002-of-00003.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.4.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.sinks": "model-00002-of-00003.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.5.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.5.self_attn.sinks": "model-00003-of-00003.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.6.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.sinks": "model-00003-of-00003.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.7.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.sinks": "model-00003-of-00003.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "mask_embed": "model-00003-of-00003.safetensors",
+    "norm.weight": "model-00003-of-00003.safetensors"
+  }
+}