ashxhart commited on
Commit
183cc1c
·
verified ·
1 Parent(s): 24f6934

Standardize bundled DFlash checkpoint filename

Browse files
README.md CHANGED
@@ -40,7 +40,7 @@ The checkpoint includes its native three-layer MTP payload in `mtp/model_mtp.saf
40
  | Native component | Path | Format |
41
  | --- | --- | --- |
42
  | MTP predictor | `mtp/model_mtp.safetensors` | MLX 4-bit affine |
43
- | DFlash drafter | `dflash/dflash_draft_model.safetensors` | Upstream BF16 |
44
  | Vision encoder | `omnimodal/vision_encoder.safetensors` | Upstream BF16 |
45
  | Audio encoder | `omnimodal/audio_encoder.safetensors` | Upstream BF16 |
46
  | Audio tokenizer | `audio_tokenizer/model.safetensors` | Upstream weights |
 
40
  | Native component | Path | Format |
41
  | --- | --- | --- |
42
  | MTP predictor | `mtp/model_mtp.safetensors` | MLX 4-bit affine |
43
+ | DFlash drafter | `dflash/model.safetensors` | Upstream BF16 |
44
  | Vision encoder | `omnimodal/vision_encoder.safetensors` | Upstream BF16 |
45
  | Audio encoder | `omnimodal/audio_encoder.safetensors` | Upstream BF16 |
46
  | Audio tokenizer | `audio_tokenizer/model.safetensors` | Upstream weights |
dflash/{dflash_draft_model.safetensors → model.safetensors} RENAMED
File without changes
dflash/model.safetensors.index.json CHANGED
@@ -3,68 +3,68 @@
3
  "total_size": 2936114304
4
  },
5
  "weight_map": {
6
- "fc.weight": "dflash_draft_model.safetensors",
7
- "hidden_norm.weight": "dflash_draft_model.safetensors",
8
- "norm.weight": "dflash_draft_model.safetensors",
9
- "layers.0.input_layernorm.weight": "dflash_draft_model.safetensors",
10
- "layers.0.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
11
- "layers.0.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
12
- "layers.0.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
13
- "layers.0.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
14
- "layers.0.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
15
- "layers.0.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
16
- "layers.0.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
17
- "layers.0.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
18
- "layers.0.mlp.up_proj.weight": "dflash_draft_model.safetensors",
19
- "layers.0.mlp.down_proj.weight": "dflash_draft_model.safetensors",
20
- "layers.0.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
21
- "layers.1.input_layernorm.weight": "dflash_draft_model.safetensors",
22
- "layers.1.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
23
- "layers.1.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
24
- "layers.1.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
25
- "layers.1.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
26
- "layers.1.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
27
- "layers.1.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
28
- "layers.1.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
29
- "layers.1.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
30
- "layers.1.mlp.up_proj.weight": "dflash_draft_model.safetensors",
31
- "layers.1.mlp.down_proj.weight": "dflash_draft_model.safetensors",
32
- "layers.1.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
33
- "layers.2.input_layernorm.weight": "dflash_draft_model.safetensors",
34
- "layers.2.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
35
- "layers.2.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
36
- "layers.2.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
37
- "layers.2.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
38
- "layers.2.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
39
- "layers.2.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
40
- "layers.2.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
41
- "layers.2.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
42
- "layers.2.mlp.up_proj.weight": "dflash_draft_model.safetensors",
43
- "layers.2.mlp.down_proj.weight": "dflash_draft_model.safetensors",
44
- "layers.2.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
45
- "layers.3.input_layernorm.weight": "dflash_draft_model.safetensors",
46
- "layers.3.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
47
- "layers.3.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
48
- "layers.3.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
49
- "layers.3.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
50
- "layers.3.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
51
- "layers.3.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
52
- "layers.3.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
53
- "layers.3.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
54
- "layers.3.mlp.up_proj.weight": "dflash_draft_model.safetensors",
55
- "layers.3.mlp.down_proj.weight": "dflash_draft_model.safetensors",
56
- "layers.3.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
57
- "layers.4.input_layernorm.weight": "dflash_draft_model.safetensors",
58
- "layers.4.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
59
- "layers.4.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
60
- "layers.4.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
61
- "layers.4.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
62
- "layers.4.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
63
- "layers.4.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
64
- "layers.4.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
65
- "layers.4.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
66
- "layers.4.mlp.up_proj.weight": "dflash_draft_model.safetensors",
67
- "layers.4.mlp.down_proj.weight": "dflash_draft_model.safetensors",
68
- "layers.4.self_attn.attention_sink_bias": "dflash_draft_model.safetensors"
69
  }
70
  }
 
3
  "total_size": 2936114304
4
  },
5
  "weight_map": {
6
+ "fc.weight": "model.safetensors",
7
+ "hidden_norm.weight": "model.safetensors",
8
+ "norm.weight": "model.safetensors",
9
+ "layers.0.input_layernorm.weight": "model.safetensors",
10
+ "layers.0.post_attention_layernorm.weight": "model.safetensors",
11
+ "layers.0.self_attn.q_norm.weight": "model.safetensors",
12
+ "layers.0.self_attn.k_norm.weight": "model.safetensors",
13
+ "layers.0.self_attn.q_proj.weight": "model.safetensors",
14
+ "layers.0.self_attn.k_proj.weight": "model.safetensors",
15
+ "layers.0.self_attn.v_proj.weight": "model.safetensors",
16
+ "layers.0.self_attn.o_proj.weight": "model.safetensors",
17
+ "layers.0.mlp.gate_proj.weight": "model.safetensors",
18
+ "layers.0.mlp.up_proj.weight": "model.safetensors",
19
+ "layers.0.mlp.down_proj.weight": "model.safetensors",
20
+ "layers.0.self_attn.attention_sink_bias": "model.safetensors",
21
+ "layers.1.input_layernorm.weight": "model.safetensors",
22
+ "layers.1.post_attention_layernorm.weight": "model.safetensors",
23
+ "layers.1.self_attn.q_norm.weight": "model.safetensors",
24
+ "layers.1.self_attn.k_norm.weight": "model.safetensors",
25
+ "layers.1.self_attn.q_proj.weight": "model.safetensors",
26
+ "layers.1.self_attn.k_proj.weight": "model.safetensors",
27
+ "layers.1.self_attn.v_proj.weight": "model.safetensors",
28
+ "layers.1.self_attn.o_proj.weight": "model.safetensors",
29
+ "layers.1.mlp.gate_proj.weight": "model.safetensors",
30
+ "layers.1.mlp.up_proj.weight": "model.safetensors",
31
+ "layers.1.mlp.down_proj.weight": "model.safetensors",
32
+ "layers.1.self_attn.attention_sink_bias": "model.safetensors",
33
+ "layers.2.input_layernorm.weight": "model.safetensors",
34
+ "layers.2.post_attention_layernorm.weight": "model.safetensors",
35
+ "layers.2.self_attn.q_norm.weight": "model.safetensors",
36
+ "layers.2.self_attn.k_norm.weight": "model.safetensors",
37
+ "layers.2.self_attn.q_proj.weight": "model.safetensors",
38
+ "layers.2.self_attn.k_proj.weight": "model.safetensors",
39
+ "layers.2.self_attn.v_proj.weight": "model.safetensors",
40
+ "layers.2.self_attn.o_proj.weight": "model.safetensors",
41
+ "layers.2.mlp.gate_proj.weight": "model.safetensors",
42
+ "layers.2.mlp.up_proj.weight": "model.safetensors",
43
+ "layers.2.mlp.down_proj.weight": "model.safetensors",
44
+ "layers.2.self_attn.attention_sink_bias": "model.safetensors",
45
+ "layers.3.input_layernorm.weight": "model.safetensors",
46
+ "layers.3.post_attention_layernorm.weight": "model.safetensors",
47
+ "layers.3.self_attn.q_norm.weight": "model.safetensors",
48
+ "layers.3.self_attn.k_norm.weight": "model.safetensors",
49
+ "layers.3.self_attn.q_proj.weight": "model.safetensors",
50
+ "layers.3.self_attn.k_proj.weight": "model.safetensors",
51
+ "layers.3.self_attn.v_proj.weight": "model.safetensors",
52
+ "layers.3.self_attn.o_proj.weight": "model.safetensors",
53
+ "layers.3.mlp.gate_proj.weight": "model.safetensors",
54
+ "layers.3.mlp.up_proj.weight": "model.safetensors",
55
+ "layers.3.mlp.down_proj.weight": "model.safetensors",
56
+ "layers.3.self_attn.attention_sink_bias": "model.safetensors",
57
+ "layers.4.input_layernorm.weight": "model.safetensors",
58
+ "layers.4.post_attention_layernorm.weight": "model.safetensors",
59
+ "layers.4.self_attn.q_norm.weight": "model.safetensors",
60
+ "layers.4.self_attn.k_norm.weight": "model.safetensors",
61
+ "layers.4.self_attn.q_proj.weight": "model.safetensors",
62
+ "layers.4.self_attn.k_proj.weight": "model.safetensors",
63
+ "layers.4.self_attn.v_proj.weight": "model.safetensors",
64
+ "layers.4.self_attn.o_proj.weight": "model.safetensors",
65
+ "layers.4.mlp.gate_proj.weight": "model.safetensors",
66
+ "layers.4.mlp.up_proj.weight": "model.safetensors",
67
+ "layers.4.mlp.down_proj.weight": "model.safetensors",
68
+ "layers.4.self_attn.attention_sink_bias": "model.safetensors"
69
  }
70
  }