Commit
•
a7fa264
1
Parent(s):
258e561
upload model
Browse files- config.json +29 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +649 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +187 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_bias": true,
|
3 |
+
"attention_dropout": 0.1,
|
4 |
+
"attention_multiplier": null,
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"eos_token_id": 0,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 2304,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 9216,
|
11 |
+
"m_emb": 12.0,
|
12 |
+
"m_residual": 0.22,
|
13 |
+
"m_width": 9.0,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"mlp_bias": true,
|
16 |
+
"model_type": "granite",
|
17 |
+
"num_attention_heads": 36,
|
18 |
+
"num_hidden_layers": 40,
|
19 |
+
"num_key_value_heads": 36,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000,
|
25 |
+
"tie_word_embeddings": true,
|
26 |
+
"transformers_version": "4.43.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 49152
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.43.0.dev0"
|
7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95acd667761626499c699bdcfc414f081d1ac934853f85a6869ae7e8385d7830
|
3 |
+
size 6528305120
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c507a29a79daf7bb91592a2b13f3e86639ac61d8c7f0d3ba7e8be8d540fb482
|
3 |
+
size 6670161488
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1f47a5ff696b4b101d44319e509ab47399f46fd241726d8c62a7b63aac1de7a
|
3 |
+
size 849673784
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,649 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 10649207808
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"model.norm.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
27 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
28 |
+
"model.layers.1.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.1.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"model.layers.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
36 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
38 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
39 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
40 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
41 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
42 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
43 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
44 |
+
"model.layers.2.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
45 |
+
"model.layers.2.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
46 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
47 |
+
"model.layers.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
48 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
49 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
50 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
51 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
52 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
53 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
54 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
55 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
56 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
57 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
58 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
59 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
60 |
+
"model.layers.3.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
61 |
+
"model.layers.3.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
62 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
63 |
+
"model.layers.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
64 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
65 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
66 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
67 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
68 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
69 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
70 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
71 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
72 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
73 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
74 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
75 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
76 |
+
"model.layers.4.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
77 |
+
"model.layers.4.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
78 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
79 |
+
"model.layers.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
80 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
81 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
82 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
83 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
84 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
85 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
86 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
87 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
88 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
89 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
90 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
91 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
92 |
+
"model.layers.5.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
93 |
+
"model.layers.5.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
94 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
95 |
+
"model.layers.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
96 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
97 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
98 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
99 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
100 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
101 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
102 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
103 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
104 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
105 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
106 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
107 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
108 |
+
"model.layers.6.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
109 |
+
"model.layers.6.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
110 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
111 |
+
"model.layers.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
112 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
113 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
114 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
115 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
116 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.7.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.7.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
126 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
127 |
+
"model.layers.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
128 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
129 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
130 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
131 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
132 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
133 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
134 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
135 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
136 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
137 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
138 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
139 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
140 |
+
"model.layers.8.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
141 |
+
"model.layers.8.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
142 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
143 |
+
"model.layers.8.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
144 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
145 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
146 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
147 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
148 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
149 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
150 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
151 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
152 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
153 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
154 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
155 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
156 |
+
"model.layers.9.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
157 |
+
"model.layers.9.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
158 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
159 |
+
"model.layers.9.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
160 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
161 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
162 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
163 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
164 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
165 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
166 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
167 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
168 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
169 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
170 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
171 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
172 |
+
"model.layers.10.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
173 |
+
"model.layers.10.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
174 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
175 |
+
"model.layers.10.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
176 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
177 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
178 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
179 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
180 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
181 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
182 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
183 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
184 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
185 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
186 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
187 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
188 |
+
"model.layers.11.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
189 |
+
"model.layers.11.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
190 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
191 |
+
"model.layers.11.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
192 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
193 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
194 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
195 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
196 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
197 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
198 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
199 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
200 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
201 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
202 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
203 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
204 |
+
"model.layers.12.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
205 |
+
"model.layers.12.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
206 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
207 |
+
"model.layers.12.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
208 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
209 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
210 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
211 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
212 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
213 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
214 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
215 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.13.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.13.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.13.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
225 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
226 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
227 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
228 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
229 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
230 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
231 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
232 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
233 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
234 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
235 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
236 |
+
"model.layers.14.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
237 |
+
"model.layers.14.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
238 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
239 |
+
"model.layers.14.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
240 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
242 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.15.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.15.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.15.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.16.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.16.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.16.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.17.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.17.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.17.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
291 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
292 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
293 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
294 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
295 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
296 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
297 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
298 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
299 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
300 |
+
"model.layers.18.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
301 |
+
"model.layers.18.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
302 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
303 |
+
"model.layers.18.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
304 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
305 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
306 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
307 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
308 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
309 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
310 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
311 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
312 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
313 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
314 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
315 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
316 |
+
"model.layers.19.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
317 |
+
"model.layers.19.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
318 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
319 |
+
"model.layers.19.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
320 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
321 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
322 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
323 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
324 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
325 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
326 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
327 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
328 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
329 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
330 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
331 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
332 |
+
"model.layers.20.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
333 |
+
"model.layers.20.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
334 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
335 |
+
"model.layers.20.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
336 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
337 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
338 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
339 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
340 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
341 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
342 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
343 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
344 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
345 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
346 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
347 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
348 |
+
"model.layers.21.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
349 |
+
"model.layers.21.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
350 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
351 |
+
"model.layers.21.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
352 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
353 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
354 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
355 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
356 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
357 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
358 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
359 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
360 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
361 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
362 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
363 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
364 |
+
"model.layers.22.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
365 |
+
"model.layers.22.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
366 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
367 |
+
"model.layers.22.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
368 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
369 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
370 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
371 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
372 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
373 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
374 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
375 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
376 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
377 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
378 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
379 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
380 |
+
"model.layers.23.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
381 |
+
"model.layers.23.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
382 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
383 |
+
"model.layers.23.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
384 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
385 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
386 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
387 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
388 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
389 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
390 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
391 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
392 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
393 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
394 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
395 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
396 |
+
"model.layers.24.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
397 |
+
"model.layers.24.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
398 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
399 |
+
"model.layers.24.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
400 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
401 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
402 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
403 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
404 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
405 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
406 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
407 |
+
"model.layers.24.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
408 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
409 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
410 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
411 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
412 |
+
"model.layers.25.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
413 |
+
"model.layers.25.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
414 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
415 |
+
"model.layers.25.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
416 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
417 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
418 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
419 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
420 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
421 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
422 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
423 |
+
"model.layers.25.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
424 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
425 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
426 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
427 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
428 |
+
"model.layers.26.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
429 |
+
"model.layers.26.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
430 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
431 |
+
"model.layers.26.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
432 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
433 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
434 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
435 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
436 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
437 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
438 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
439 |
+
"model.layers.26.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
440 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
441 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
442 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
443 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
444 |
+
"model.layers.27.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
445 |
+
"model.layers.27.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
446 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
447 |
+
"model.layers.27.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
448 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
449 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
450 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
451 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
452 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
453 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
454 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
455 |
+
"model.layers.27.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
456 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
457 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
458 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
459 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
460 |
+
"model.layers.28.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
461 |
+
"model.layers.28.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
462 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
463 |
+
"model.layers.28.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
464 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
465 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
466 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
467 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
468 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
469 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
470 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
471 |
+
"model.layers.28.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
472 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
473 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
474 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
475 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
476 |
+
"model.layers.29.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
477 |
+
"model.layers.29.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
478 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
479 |
+
"model.layers.29.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
480 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
481 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
482 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
483 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
484 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
485 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
486 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
487 |
+
"model.layers.29.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
488 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
489 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
490 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
491 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
492 |
+
"model.layers.30.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
493 |
+
"model.layers.30.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
494 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
495 |
+
"model.layers.30.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
496 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
497 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
498 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
499 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
500 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
501 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
502 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
503 |
+
"model.layers.30.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
504 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
505 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
506 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
507 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
508 |
+
"model.layers.31.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
509 |
+
"model.layers.31.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
510 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
511 |
+
"model.layers.31.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
512 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
513 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
514 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
515 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
516 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
517 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
518 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
519 |
+
"model.layers.31.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
520 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
521 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
522 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
523 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
524 |
+
"model.layers.32.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
525 |
+
"model.layers.32.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
526 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
527 |
+
"model.layers.32.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
528 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
529 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
530 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
531 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
532 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
533 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
534 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
535 |
+
"model.layers.32.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
536 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
537 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
538 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
539 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
540 |
+
"model.layers.33.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
541 |
+
"model.layers.33.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
542 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
543 |
+
"model.layers.33.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
544 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
545 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
546 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
547 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
548 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
549 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
550 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
551 |
+
"model.layers.33.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
552 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
553 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
554 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
555 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
556 |
+
"model.layers.34.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
557 |
+
"model.layers.34.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
558 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
559 |
+
"model.layers.34.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
560 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
561 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
562 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
563 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
564 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
565 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
566 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
567 |
+
"model.layers.34.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
568 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
569 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
570 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
571 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
572 |
+
"model.layers.35.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
573 |
+
"model.layers.35.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
574 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
575 |
+
"model.layers.35.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
576 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
577 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
578 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
579 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
580 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
581 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
582 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
583 |
+
"model.layers.35.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
584 |
+
"model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
585 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
586 |
+
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
587 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
588 |
+
"model.layers.36.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
589 |
+
"model.layers.36.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
590 |
+
"model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
591 |
+
"model.layers.36.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
|
592 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
593 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
594 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
595 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
596 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
597 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
598 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
599 |
+
"model.layers.36.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
|
600 |
+
"model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
601 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
602 |
+
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
603 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
604 |
+
"model.layers.37.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
|
605 |
+
"model.layers.37.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
|
606 |
+
"model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
607 |
+
"model.layers.37.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
|
608 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
609 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
610 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
611 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
612 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
613 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
614 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
615 |
+
"model.layers.37.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
|
616 |
+
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
617 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
618 |
+
"model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
619 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
620 |
+
"model.layers.38.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
|
621 |
+
"model.layers.38.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
|
622 |
+
"model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
623 |
+
"model.layers.38.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
|
624 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
625 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
626 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
627 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
628 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
629 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
630 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
631 |
+
"model.layers.38.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
|
632 |
+
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
633 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
634 |
+
"model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
635 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
636 |
+
"model.layers.39.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
|
637 |
+
"model.layers.39.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
|
638 |
+
"model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
639 |
+
"model.layers.39.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
|
640 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
641 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
642 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
643 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
644 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
645 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
646 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
647 |
+
"model.layers.39.self_attn.o_proj.bias": "model-00003-of-00003.safetensors"
|
648 |
+
}
|
649 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<fim_prefix>",
|
5 |
+
"<fim_middle>",
|
6 |
+
"<fim_suffix>",
|
7 |
+
"<fim_pad>",
|
8 |
+
"<filename>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<issue_start>",
|
11 |
+
"<issue_comment>",
|
12 |
+
"<issue_closed>",
|
13 |
+
"<jupyter_start>",
|
14 |
+
"<jupyter_text>",
|
15 |
+
"<jupyter_code>",
|
16 |
+
"<jupyter_output>",
|
17 |
+
"<empty_output>",
|
18 |
+
"<commit_before>",
|
19 |
+
"<commit_msg>",
|
20 |
+
"<commit_after>",
|
21 |
+
"<reponame>"
|
22 |
+
],
|
23 |
+
"bos_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"eos_token": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"pad_token": {
|
38 |
+
"content": "<|endoftext|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<|endoftext|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<fim_prefix>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<fim_middle>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<fim_suffix>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<fim_pad>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": "<filename>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": "<gh_stars>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "<issue_start>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<issue_comment>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<issue_closed>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<jupyter_start>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<jupyter_text>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"12": {
|
101 |
+
"content": "<jupyter_code>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"13": {
|
109 |
+
"content": "<jupyter_output>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"14": {
|
117 |
+
"content": "<empty_output>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"15": {
|
125 |
+
"content": "<commit_before>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"16": {
|
133 |
+
"content": "<commit_msg>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"17": {
|
141 |
+
"content": "<commit_after>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"18": {
|
149 |
+
"content": "<reponame>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
}
|
156 |
+
},
|
157 |
+
"additional_special_tokens": [
|
158 |
+
"<|endoftext|>",
|
159 |
+
"<fim_prefix>",
|
160 |
+
"<fim_middle>",
|
161 |
+
"<fim_suffix>",
|
162 |
+
"<fim_pad>",
|
163 |
+
"<filename>",
|
164 |
+
"<gh_stars>",
|
165 |
+
"<issue_start>",
|
166 |
+
"<issue_comment>",
|
167 |
+
"<issue_closed>",
|
168 |
+
"<jupyter_start>",
|
169 |
+
"<jupyter_text>",
|
170 |
+
"<jupyter_code>",
|
171 |
+
"<jupyter_output>",
|
172 |
+
"<empty_output>",
|
173 |
+
"<commit_before>",
|
174 |
+
"<commit_msg>",
|
175 |
+
"<commit_after>",
|
176 |
+
"<reponame>"
|
177 |
+
],
|
178 |
+
"bos_token": "<|endoftext|>",
|
179 |
+
"clean_up_tokenization_spaces": true,
|
180 |
+
"eos_token": "<|endoftext|>",
|
181 |
+
"model_max_length": 9223372036854775807,
|
182 |
+
"pad_token": "<|endoftext|>",
|
183 |
+
"padding_side": "left",
|
184 |
+
"tokenizer_class": "GPT2Tokenizer",
|
185 |
+
"unk_token": "<|endoftext|>",
|
186 |
+
"vocab_size": 49152
|
187 |
+
}
|