Jlonge4 commited on
Commit
0d9afc1
·
verified ·
1 Parent(s): 66241a6

Upload folder using huggingface_hub

Browse files
.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/81a4d0d97fa68234fdc9.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/c656383dd62a0cdcdc2a.neff filter=lfs diff=lfs merge=lfs -text
compiled/81a4d0d97fa68234fdc9.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ecc2ea402cc74af75c0a0a5f2b30d5b4567aa618025d28f411712efa32ece5
3
+ size 14746624
compiled/c656383dd62a0cdcdc2a.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd1414427c66dc7f5760a6bf8aeb71b5ad4941038253046ff4097cf7611384b
3
+ size 4598784
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-4",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 100257,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 100265,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 17920,
15
+ "max_position_embeddings": 16384,
16
+ "model_type": "phi3",
17
+ "neuron": {
18
+ "auto_cast_type": "bf16",
19
+ "batch_size": 1,
20
+ "checkpoint_id": "microsoft/phi-4",
21
+ "checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61",
22
+ "compiler_type": "neuronx-cc",
23
+ "compiler_version": "2.15.143.0+e39249ad",
24
+ "num_cores": 2,
25
+ "sequence_length": 2048,
26
+ "task": "text-generation"
27
+ },
28
+ "num_attention_heads": 40,
29
+ "num_hidden_layers": 40,
30
+ "num_key_value_heads": 10,
31
+ "original_max_position_embeddings": 16384,
32
+ "pad_token_id": 100349,
33
+ "resid_pdrop": 0.0,
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 250000,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.48.3",
41
+ "use_cache": true,
42
+ "vocab_size": 100352
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100265,
5
+ "pad_token_id": 100349,
6
+ "transformers_version": "4.48.3"
7
+ }