tensor-whisperer
commited on
Commit
•
a04a1c7
1
Parent(s):
e5b46a4
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- compiled/5dba3cad55e54488bf28.neff +0 -0
- compiled/6335e5c83cb05b0e2e2f.neff +0 -0
- compiled/7769b1609ff0135ed19f.neff +3 -0
- compiled/b7908788efc11202bef0.neff +3 -0
- compiled/ffbbe0b2cfc2a5dc84b8.neff +0 -0
- config.json +43 -0
- generation_config.json +6 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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/7769b1609ff0135ed19f.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/b7908788efc11202bef0.neff filter=lfs diff=lfs merge=lfs -text
|
compiled/5dba3cad55e54488bf28.neff
ADDED
Binary file (984 kB). View file
|
|
compiled/6335e5c83cb05b0e2e2f.neff
ADDED
Binary file (953 kB). View file
|
|
compiled/7769b1609ff0135ed19f.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6ebd4b57206d88249a3d62a9b3acdaeb7dd00cd87bb28c1cc9e911d62ca381
|
3 |
+
size 1055744
|
compiled/b7908788efc11202bef0.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e430b19772fd67968d714a69667341d4d8d6d406279f2cc41b2ba76c1a207f27
|
3 |
+
size 1014784
|
compiled/ffbbe0b2cfc2a5dc84b8.neff
ADDED
Binary file (953 kB). View file
|
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Writer/palmyra-3b",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.01,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 4096,
|
15 |
+
"n_head": 32,
|
16 |
+
"n_inner": 16384,
|
17 |
+
"n_layer": 24,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"neuron": {
|
20 |
+
"auto_cast_type": "fp16",
|
21 |
+
"batch_size": 1,
|
22 |
+
"checkpoint_id": "Writer/palmyra-3b",
|
23 |
+
"checkpoint_revision": "48c1c0684cca6938da5e975c39f28d6e7d625f61",
|
24 |
+
"compiler_type": "neuronx-cc",
|
25 |
+
"compiler_version": "2.12.68.0+4480452af",
|
26 |
+
"num_cores": 32,
|
27 |
+
"sequence_length": 2048,
|
28 |
+
"task": "text-generation"
|
29 |
+
},
|
30 |
+
"reorder_and_upcast_attn": false,
|
31 |
+
"resid_pdrop": 0.1,
|
32 |
+
"scale_attn_by_inverse_layer_idx": false,
|
33 |
+
"scale_attn_weights": true,
|
34 |
+
"summary_activation": null,
|
35 |
+
"summary_first_dropout": 0.1,
|
36 |
+
"summary_proj_to_labels": true,
|
37 |
+
"summary_type": "cls_index",
|
38 |
+
"summary_use_proj": true,
|
39 |
+
"torch_dtype": "bfloat16",
|
40 |
+
"transformers_version": "4.36.2",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 50257
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|