Hugging Face's logo

aws-neuron
/
CodeLlama-7b-hf-neuron-24xlarge

Text Generation
Transformers
PyTorch
English
llama
facebook
meta
llama-2
inferentia2
neuron
text-generation-inference
Model card Files Community
3
jburtoft commited on
Commit
a46e478
•
1 Parent(s): 40f99ba

b9bb950a21cde39808336951ea1e9a7b3cfee23f83b300530f60843e20e90c2b

Browse files
Files changed (16) hide show
  1. .gitattributes +10 -0
  2. checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
  3. checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +0 -0
  4. checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +0 -0
  5. compiled/186a933115232053cdff.neff +3 -0
  6. compiled/540db8b9571300c15792.neff +3 -0
  7. compiled/585a14c8d348e11367d1.neff +3 -0
  8. compiled/6f0431e83e140df0acd9.neff +3 -0
  9. compiled/86a37b8c9f44ef0ad841.neff +3 -0
  10. compiled/c5726de0e8bc3fd6f4c9.neff +3 -0
  11. compiled/e0158d7717a18978a6c7.neff +3 -0
  12. compiled/e87cecd034e5ac4c3f36.neff +3 -0
  13. compiled/ea24e07b03ca7ec5310c.neff +3 -0
  14. compiled/fedc38910ff9aec1ce50.neff +3 -0
  15. config.json +35 -0
  16. generation_config.json +6 -0
.gitattributes CHANGED
@@ -33,3 +33,13 @@ 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/186a933115232053cdff.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/540db8b9571300c15792.neff filter=lfs diff=lfs merge=lfs -text
38
+ compiled/585a14c8d348e11367d1.neff filter=lfs diff=lfs merge=lfs -text
39
+ compiled/6f0431e83e140df0acd9.neff filter=lfs diff=lfs merge=lfs -text
40
+ compiled/86a37b8c9f44ef0ad841.neff filter=lfs diff=lfs merge=lfs -text
41
+ compiled/c5726de0e8bc3fd6f4c9.neff filter=lfs diff=lfs merge=lfs -text
42
+ compiled/e0158d7717a18978a6c7.neff filter=lfs diff=lfs merge=lfs -text
43
+ compiled/e87cecd034e5ac4c3f36.neff filter=lfs diff=lfs merge=lfs -text
44
+ compiled/ea24e07b03ca7ec5310c.neff filter=lfs diff=lfs merge=lfs -text
45
+ compiled/fedc38910ff9aec1ce50.neff filter=lfs diff=lfs merge=lfs -text
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 sha256:49b4ee604e7d7e179f251f097927f0eafc5fc52df7a9ec65044c33abf2bcf7f5
3
+ size 180355961
checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight ADDED
Binary file (17.3 kB). View file
 
checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight ADDED
Binary file (17.3 kB). View file
 
compiled/186a933115232053cdff.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69160786da7d64456c462d627ea538b521c1e205e652ac626272bd9fca90e8f
3
+ size 2089984
compiled/540db8b9571300c15792.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a84bfb02bd9717e3a69b68f152691ef81c7043b5db38f39c7e6b00e9123fbf
3
+ size 6063104
compiled/585a14c8d348e11367d1.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbc0b5edd574f055c3f5803e83af7f4e97915cf00a1d8a3b8d9a685a05b0fc2
3
+ size 2540544
compiled/6f0431e83e140df0acd9.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb2ef439563483fc3b4211c0845e803b09bf5e895f6e80ab70f0b54af2e5072
3
+ size 1926144
compiled/86a37b8c9f44ef0ad841.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119e92e72b33584291189b6fce4a3b79a26a6255e83f4d5594231d5a70474afc
3
+ size 2325504
compiled/c5726de0e8bc3fd6f4c9.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efa15e75ba5f483fb9971a39a5131e3297f269070cddebdec54e812be1959b3
3
+ size 1956864
compiled/e0158d7717a18978a6c7.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b544ef3fc52e2f08e060887b57f3a9fb2164e75892e284d18b207b9f66a208b
3
+ size 2110464
compiled/e87cecd034e5ac4c3f36.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4388c145d3a889fdbb1471239d43009f68cf5674d849cd4b7793861b2ff6c7ed
3
+ size 2008064
compiled/ea24e07b03ca7ec5310c.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cecce50f04ef6df235609bc58c4cb3405200cd55213e47c403e2ca99b2e5002a
3
+ size 2018304
compiled/fedc38910ff9aec1ce50.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1d80b55a30d51e1d7844e35c009d8af2055e360a8c555c99fc55d75362a5e1
3
+ size 2284544
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CodeLlama-7b-hf/config.json",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 16384,
13
+ "model_type": "llama",
14
+ "neuron": {
15
+ "auto_cast_type": "fp16",
16
+ "batch_size": 1,
17
+ "compiler_type": "neuronx-cc",
18
+ "compiler_version": "2.11.0.34+c5231f848",
19
+ "num_cores": 12,
20
+ "sequence_length": 2048,
21
+ "task": "text-generation"
22
+ },
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 32,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.33.2",
33
+ "use_cache": true,
34
+ "vocab_size": 32016
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
+ }