Add files using upload-large-folder tool

dflash-32b-draft-v2test-phaseL-int4mlp-gptq/config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "DFlashDraftModel"
+  ],
+  "model_type": "qwen3",
+  "hidden_size": 5120,
+  "intermediate_size": 13824,
+  "num_hidden_layers": 8,
+  "num_attention_heads": 40,
+  "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": 500000.0,
+  "rope_scaling": null,
+  "sliding_window": 512,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "block_size": 11,
+  "num_target_layers": 64,
+  "target_hidden_size": 5120,
+  "torch_dtype": "bfloat16",
+  "tie_word_embeddings": false,
+  "dflash_config": {
+    "mask_token_id": 128000,
+    "target_layer_ids": [
+      1,
+      10,
+      18,
+      27,
+      35,
+      44,
+      52,
+      61
+    ],
+    "num_target_layers": 64,
+    "block_size": 11,
+    "use_attention_sink": true,
+    "sliding_window": 512
+  },
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "format": "pack-quantized",
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 4,
+          "type": "int",
+          "symmetric": true,
+          "strategy": "group",
+          "group_size": 128,
+          "actorder": null,
+          "dynamic": false
+        }
+      }
+    },
+    "ignore": [
+      "re:.*self_attn.*"
+    ]
+  }
+}

dflash-32b-draft-v2test-phaseL-int4mlp-gptq/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7828a3a928305f4f0f1c068bd6afa39e661fe8da744c3550f8e825e2b3b1cccc
+size 1198482240

dflash-32b-draft-v2test-phaseL-int4mlp-gptq/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0cbf7f55a8f0ba2b29a3c3be6893e88923989a5d041ed7f3cca4725d64bd08
+size 1103779280

dflash-32b-draft-v2test-phaseL-int4mlp-gptq/model.safetensors.index.json

@@ -0,0 +1,155 @@
+{
+  "metadata": {
+    "total_size": 2302245888
+  },
+  "weight_map": {
+    "fc.weight": "model-00001-of-00002.safetensors",
+    "hidden_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.sinks": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.sinks": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.sinks": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.sinks": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.sinks": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.sinks": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.sinks": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.sinks": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "mask_embed": "model-00002-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors"
+  }
+}