update
Browse files
README.md
CHANGED
@@ -1,3 +1,77 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
|
5 |
+
PhiConfig {
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"embd_pdrop": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu_new",
|
11 |
+
"hidden_size": 8,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 10,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 2048,
|
16 |
+
"model_type": "phi",
|
17 |
+
"num_attention_heads": 4,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"num_key_value_heads": 2,
|
20 |
+
"partial_rotary_factor": 0.5,
|
21 |
+
"qk_layernorm": false,
|
22 |
+
"resid_pdrop": 0.0,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 20
|
29 |
+
}
|
30 |
+
|
31 |
+
PhiForCausalLM(
|
32 |
+
(model): PhiModel(
|
33 |
+
(embed_tokens): Embedding(20, 8)
|
34 |
+
(embed_dropout): Dropout(p=0.0, inplace=False)
|
35 |
+
(layers): ModuleList(
|
36 |
+
(0-5): 6 x PhiDecoderLayer(
|
37 |
+
(self_attn): PhiAttention(
|
38 |
+
(q_proj): Linear(in_features=8, out_features=8, bias=True)
|
39 |
+
(k_proj): Linear(in_features=8, out_features=4, bias=True)
|
40 |
+
(v_proj): Linear(in_features=8, out_features=4, bias=True)
|
41 |
+
(dense): Linear(in_features=8, out_features=8, bias=True)
|
42 |
+
(rotary_emb): PhiRotaryEmbedding()
|
43 |
+
)
|
44 |
+
(mlp): PhiMLP(
|
45 |
+
(activation_fn): NewGELUActivation()
|
46 |
+
(fc1): Linear(in_features=8, out_features=10, bias=True)
|
47 |
+
(fc2): Linear(in_features=10, out_features=8, bias=True)
|
48 |
+
)
|
49 |
+
(input_layernorm): LayerNorm((8,), eps=1e-05, elementwise_affine=True)
|
50 |
+
(resid_dropout): Dropout(p=0.0, inplace=False)
|
51 |
+
)
|
52 |
+
)
|
53 |
+
(final_layernorm): LayerNorm((8,), eps=1e-05, elementwise_affine=True)
|
54 |
+
)
|
55 |
+
(lm_head): Linear(in_features=8, out_features=20, bias=True)
|
56 |
+
)
|
57 |
+
===========================================================================
|
58 |
+
Layer (type:depth-idx) Param #
|
59 |
+
===========================================================================
|
60 |
+
PhiForCausalLM --
|
61 |
+
├─PhiModel: 1-1 --
|
62 |
+
│ └─Embedding: 2-1 160
|
63 |
+
│ └─Dropout: 2-2 --
|
64 |
+
│ └─ModuleList: 2-3 --
|
65 |
+
│ │ └─PhiDecoderLayer: 3-1 410
|
66 |
+
│ │ └─PhiDecoderLayer: 3-2 410
|
67 |
+
│ │ └─PhiDecoderLayer: 3-3 410
|
68 |
+
│ │ └─PhiDecoderLayer: 3-4 410
|
69 |
+
│ │ └─PhiDecoderLayer: 3-5 410
|
70 |
+
│ │ └─PhiDecoderLayer: 3-6 410
|
71 |
+
│ └─LayerNorm: 2-4 16
|
72 |
+
├─Linear: 1-2 180
|
73 |
+
===========================================================================
|
74 |
+
Total params: 2,816
|
75 |
+
Trainable params: 2,816
|
76 |
+
Non-trainable params: 0
|
77 |
+
===========================================================================
|