a4cbd700fcb4c8fb8e5ad8939c45cd6a36e98110eb7cfb4d4a54bb7b5acd64a1
Browse files- .gitattributes +12 -0
- checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +3 -0
- compiled/1676675da8f4c4a45672.neff +3 -0
- compiled/26fcb9b7474720361781.neff +3 -0
- compiled/2e28464daacb0d71b0f9.neff +3 -0
- compiled/588db7b5ee3cd1d94818.neff +3 -0
- compiled/5d3941cd4a2c11eb2b53.neff +3 -0
- compiled/6d1ce4f303e6acb3ac78.neff +3 -0
- compiled/a0e4cadc2c5dfb35ca3f.neff +3 -0
- compiled/a133003370caedcd9321.neff +3 -0
- compiled/a5865af3b03497c067ef.neff +3 -0
- compiled/b13e3f0a11e384d8d234.neff +3 -0
- compiled/bb3fb24dd2ac312b2da0.neff +3 -0
- compiled/fd71de5cbaf4ff11feb5.neff +3 -0
- config.json +36 -0
- generation_config.json +7 -0
.gitattributes
CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
compiled/1676675da8f4c4a45672.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/26fcb9b7474720361781.neff filter=lfs diff=lfs merge=lfs -text
|
38 |
+
compiled/2e28464daacb0d71b0f9.neff filter=lfs diff=lfs merge=lfs -text
|
39 |
+
compiled/588db7b5ee3cd1d94818.neff filter=lfs diff=lfs merge=lfs -text
|
40 |
+
compiled/5d3941cd4a2c11eb2b53.neff filter=lfs diff=lfs merge=lfs -text
|
41 |
+
compiled/6d1ce4f303e6acb3ac78.neff filter=lfs diff=lfs merge=lfs -text
|
42 |
+
compiled/a0e4cadc2c5dfb35ca3f.neff filter=lfs diff=lfs merge=lfs -text
|
43 |
+
compiled/a133003370caedcd9321.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
+
compiled/a5865af3b03497c067ef.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
+
compiled/b13e3f0a11e384d8d234.neff filter=lfs diff=lfs merge=lfs -text
|
46 |
+
compiled/bb3fb24dd2ac312b2da0.neff filter=lfs diff=lfs merge=lfs -text
|
47 |
+
compiled/fd71de5cbaf4ff11feb5.neff filter=lfs diff=lfs merge=lfs -text
|
checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74683202298c1169204db85d4ed1ec4a3a290842514f9d0f08712a2847cff978
|
3 |
+
size 234881907
|
checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b18e40da9aa716cc43ad956c29e5803432bfa92e3e2ff8faab1954d7328689
|
3 |
+
size 234881913
|
checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bea41eed83a51615160744f6eb14caefc5be5dc2b34fc1545f984e8ce61a2c3
|
3 |
+
size 17279
|
checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d6dba5a09d7bee70951d68ce54cf1f362cf3ccfacda246b10d9bd3055123e9
|
3 |
+
size 17306
|
compiled/1676675da8f4c4a45672.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0922a7ad2aef4b3fc7a62fb0474fc3ae0dc16fb536a4600a082cfdc9919c1828
|
3 |
+
size 3267584
|
compiled/26fcb9b7474720361781.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b6ce6b5ae7906b197b6c6415ff81836ad567e9f8e0bfda7cc78d4997c4586fd
|
3 |
+
size 3421184
|
compiled/2e28464daacb0d71b0f9.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbcd3e97741fe2b3c01b685298a7e30a837004f5d8af54b025ec504015be0e63
|
3 |
+
size 2980864
|
compiled/588db7b5ee3cd1d94818.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef3f83c58fe2819c28ba7166b9eb71bb5b8dbe95bc986240ebbae2b688cdb71
|
3 |
+
size 3605504
|
compiled/5d3941cd4a2c11eb2b53.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7ef2184435cfb77d4474a59d6574743ed4f329372a4335997ed544b70470722
|
3 |
+
size 3257344
|
compiled/6d1ce4f303e6acb3ac78.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcf17423b04b577c4abba3471bc078db5933b28fb02ec91e3b2a712cf3bd6976
|
3 |
+
size 3687424
|
compiled/a0e4cadc2c5dfb35ca3f.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4210d046d2ab16f2a7875b1152d059219c0f431a79ed858d4e654ae327559cf
|
3 |
+
size 4598784
|
compiled/a133003370caedcd9321.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a8137b0a213583e02a62bd02abf5e2ac430f7de2ab258e5f9361fe3fca5368
|
3 |
+
size 2939904
|
compiled/a5865af3b03497c067ef.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:497c9418919830a4c117656c37ff0fbf5983f9b4c1c057e8a6b3b5cbb144b1cf
|
3 |
+
size 8705024
|
compiled/b13e3f0a11e384d8d234.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e5634a5d47d1c9eaf3bf70832a4c5249fccbb43dab50c3c860116663574e3f
|
3 |
+
size 18074624
|
compiled/bb3fb24dd2ac312b2da0.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b45fde14481ba5d9ccac8300fea802a3aee1e2546e0b6afa0cdde52527222f2e
|
3 |
+
size 3032064
|
compiled/fd71de5cbaf4ff11feb5.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:140d6b721454982aba0718ee23574883fe033951647b2a4d78c324ee3092be3e
|
3 |
+
size 3093504
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SOLAR-10.7B-v1.0/config.json",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "llama",
|
15 |
+
"neuron": {
|
16 |
+
"auto_cast_type": "fp16",
|
17 |
+
"batch_size": 1,
|
18 |
+
"compiler_type": "neuronx-cc",
|
19 |
+
"compiler_version": "2.12.54.0+f631c2365",
|
20 |
+
"num_cores": 12,
|
21 |
+
"sequence_length": 4096,
|
22 |
+
"task": "text-generation"
|
23 |
+
},
|
24 |
+
"num_attention_heads": 32,
|
25 |
+
"num_hidden_layers": 48,
|
26 |
+
"num_key_value_heads": 8,
|
27 |
+
"pretraining_tp": 1,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": null,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "float16",
|
33 |
+
"transformers_version": "4.35.0",
|
34 |
+
"use_cache": false,
|
35 |
+
"vocab_size": 32000
|
36 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.35.0",
|
6 |
+
"use_cache": false
|
7 |
+
}
|