tensor-whisperer commited on
Commit
92e5546
1 Parent(s): 75c04ff

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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/6f7267709ebe2df94b94.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/7335abba82eec1f81054.neff filter=lfs diff=lfs merge=lfs -text
38
+ compiled/97a194c20ab7e279631c.neff filter=lfs diff=lfs merge=lfs -text
39
+ compiled/ae5449e52855d05c3945.neff filter=lfs diff=lfs merge=lfs -text
40
+ compiled/e20fdb08865f56a45a7b.neff filter=lfs diff=lfs merge=lfs -text
compiled/6f7267709ebe2df94b94.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:767c230e61db25fd8b8deb85737cd1077a2496212cde04fd8dee02f828df570b
3
+ size 2980864
compiled/7335abba82eec1f81054.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e5e637b69af77201a318a580e9fc330933d73079262d86fa613b9237b07bd0
3
+ size 2847744
compiled/97a194c20ab7e279631c.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fee6bd030225e8cd54e9a2455b5d3fc227f55838247655a4f30e831e0fb68f4
3
+ size 3103744
compiled/ae5449e52855d05c3945.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f2416bab38115fc74188297f4f65a6465d55f1f26e6a25f791641d4a0c79a6
3
+ size 2909184
compiled/e20fdb08865f56a45a7b.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ee0e6cd19f3131c7e9b3fdb21126201aaacf32f28db3a6edc587d9a6910cd5
3
+ size 2857984
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Writer/palmyra-20b-chat",
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": 0.008165,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 6144,
15
+ "n_head": 48,
16
+ "n_inner": 24576,
17
+ "n_layer": 44,
18
+ "n_positions": 2048,
19
+ "neuron": {
20
+ "auto_cast_type": "fp16",
21
+ "batch_size": 1,
22
+ "checkpoint_id": "Writer/palmyra-20b-chat",
23
+ "checkpoint_revision": "40d794f1c1ead098efd73f502bc50420a654cc45",
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
+ "pad_token_id": 50257,
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.36.2",
42
+ "use_cache": false,
43
+ "vocab_size": 50258
44
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50257,
6
+ "transformers_version": "4.36.2",
7
+ "use_cache": false
8
+ }