crumb commited on
Commit
4631560
·
verified ·
1 Parent(s): 33b3eae

Upload model

Browse files
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
 
2
  "activation_function": "silu",
3
  "architectures": [
4
  "PlusModelForCausalLM"
5
  ],
6
  "auto_map": {
7
- "AutoConfig": "configuration_nano.NanoConfig",
8
- "AutoModelForCausalLM": "modeling_nano.PlusModelForCausalLM"
9
  },
10
  "bos_token_id": 1,
11
  "combined_qkv": true,
@@ -34,6 +35,6 @@
34
  "torch_dtype": "bfloat16",
35
  "transformers_version": "4.36.2",
36
  "use_bias": false,
37
- "use_cache": true,
38
  "vocab_size": 32000
39
  }
 
1
  {
2
+ "_name_or_path": "crumb/parallama-p8192-medium-init",
3
  "activation_function": "silu",
4
  "architectures": [
5
  "PlusModelForCausalLM"
6
  ],
7
  "auto_map": {
8
+ "AutoConfig": "crumb/parallama-p8192-medium-init--configuration_nano.NanoConfig",
9
+ "AutoModelForCausalLM": "crumb/parallama-p8192-medium-init--modeling_nano.PlusModelForCausalLM"
10
  },
11
  "bos_token_id": 1,
12
  "combined_qkv": true,
 
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.36.2",
37
  "use_bias": false,
38
+ "use_cache": false,
39
  "vocab_size": 32000
40
  }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b91abf6b8832225346cab97204d4680c33f20dce9122d536cebf3ab10be4815
3
+ size 1072507296
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94eb0a6ddf3ca3e064509cb148351dd0412f26b21cebe49449107e9f222ea2fc
3
+ size 17825920
model.safetensors.index.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1090322176
4
+ },
5
+ "weight_map": {
6
+ "lm_head.0.weight": "model-00002-of-00002.safetensors",
7
+ "transformer.h.0.attn.out.weight": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln1.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln2.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.1.attn.out.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.1.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.1.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.1.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.ln1.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.ln2.weight": "model-00001-of-00002.safetensors",
21
+ "transformer.h.10.attn.out.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.10.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.10.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
25
+ "transformer.h.10.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.10.ln1.weight": "model-00001-of-00002.safetensors",
27
+ "transformer.h.10.ln2.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.11.attn.out.weight": "model-00001-of-00002.safetensors",
29
+ "transformer.h.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.11.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
31
+ "transformer.h.11.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.11.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.11.ln1.weight": "model-00001-of-00002.safetensors",
34
+ "transformer.h.11.ln2.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.12.attn.out.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.12.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.12.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.12.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.12.ln1.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.12.ln2.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.13.attn.out.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.13.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.13.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.13.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "transformer.h.13.ln1.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.13.ln2.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.2.attn.out.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
51
+ "transformer.h.2.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.2.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
53
+ "transformer.h.2.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.2.ln1.weight": "model-00001-of-00002.safetensors",
55
+ "transformer.h.2.ln2.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.3.attn.out.weight": "model-00001-of-00002.safetensors",
57
+ "transformer.h.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.3.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.3.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "transformer.h.3.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.3.ln1.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.3.ln2.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.4.attn.out.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.4.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.4.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.4.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.4.ln1.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.4.ln2.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.5.attn.out.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.5.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "transformer.h.5.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.5.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.5.ln1.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.5.ln2.weight": "model-00001-of-00002.safetensors",
77
+ "transformer.h.6.attn.out.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
79
+ "transformer.h.6.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.6.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
81
+ "transformer.h.6.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.6.ln1.weight": "model-00001-of-00002.safetensors",
83
+ "transformer.h.6.ln2.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.7.attn.out.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
86
+ "transformer.h.7.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.7.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.7.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.7.ln1.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.7.ln2.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.8.attn.out.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.8.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.8.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.8.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.8.ln1.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.8.ln2.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.9.attn.out.weight": "model-00001-of-00002.safetensors",
99
+ "transformer.h.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.9.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.9.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.9.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
103
+ "transformer.h.9.ln1.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.9.ln2.weight": "model-00001-of-00002.safetensors",
105
+ "transformer.ln_f.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.wte.0.weight": "model-00001-of-00002.safetensors",
107
+ "transformer.wte.1.bias": "model-00001-of-00002.safetensors",
108
+ "transformer.wte.1.weight": "model-00001-of-00002.safetensors"
109
+ }
110
+ }