Hugging Face's logo

jburtoft
/
NousResearch-Llama-2-13b-hf-seqlen-1000-bs-1-cores-2

Text Generation
Transformers
llama
Inference Endpoints
text-generation-inference
Model card Files Community
1
jburtoft commited on
Commit
4c10474
•
1 Parent(s): cfe4ac8

798b07fac8c0174c766a21cdc65a3f93d5dbc04e577b96a8019539b7ed09e6c4

Browse files
Files changed (29) hide show
  1. .gitattributes +8 -0
  2. checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight +3 -0
  3. checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight +3 -0
  4. checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight +3 -0
  5. checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight +3 -0
  6. checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight +3 -0
  7. checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight +3 -0
  8. checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight +3 -0
  9. checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight +3 -0
  10. checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight +3 -0
  11. checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight +3 -0
  12. checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight +3 -0
  13. checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +3 -0
  14. checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
  15. checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +3 -0
  16. checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +3 -0
  17. compiled/043ef3de2405203f7bd3.neff +3 -0
  18. compiled/0a7ed4c30b45af937a34.neff +3 -0
  19. compiled/808b62be7f2953e68ae6.neff +3 -0
  20. compiled/8eb82f172ecf7451bd42.neff +3 -0
  21. compiled/9086e4272d7b57eb390e.neff +3 -0
  22. compiled/b7d11aba4f1cba2bfcd3.neff +3 -0
  23. compiled/de2d44d1c147da9b9efc.neff +3 -0
  24. compiled/fc06285e6b30438b6252.neff +3 -0
  25. config.json +40 -0
  26. special_tokens_map.json +30 -0
  27. tokenizer.json +0 -0
  28. tokenizer.model +3 -0
  29. tokenizer_config.json +41 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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/043ef3de2405203f7bd3.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/0a7ed4c30b45af937a34.neff filter=lfs diff=lfs merge=lfs -text
38
+ compiled/808b62be7f2953e68ae6.neff filter=lfs diff=lfs merge=lfs -text
39
+ compiled/8eb82f172ecf7451bd42.neff filter=lfs diff=lfs merge=lfs -text
40
+ compiled/9086e4272d7b57eb390e.neff filter=lfs diff=lfs merge=lfs -text
41
+ compiled/b7d11aba4f1cba2bfcd3.neff filter=lfs diff=lfs merge=lfs -text
42
+ compiled/de2d44d1c147da9b9efc.neff filter=lfs diff=lfs merge=lfs -text
43
+ compiled/fc06285e6b30438b6252.neff filter=lfs diff=lfs merge=lfs -text
checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa8cd9d13745f57ffa672feb344e55c3f89247b4303503959cff76826786ce0
3
+ size 141558646
checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55109db35723d0982009df5060e05319c097e312ae0b02a56c957b0a7be9c61
3
+ size 141558640
checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37ee92c13605882e54106b404b2b9374f46c583e2c7504e28d6644138a2a096
3
+ size 141558646
checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da255ff3176ee85e4e7fc39566ad50796662bde76e387d05df584b3cd7964eff
3
+ size 11132
checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6f1b863cdf5563bced525c1d96b286465a8ad05c6e81566d21393dd8291cc4
3
+ size 11156
checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c173a051d720986885c099c57c63d9a7fc293140f789462aebf3ccd90dd34f93
3
+ size 11159
checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ce79fd72da0acafdea65875aed15b8458a480e49be5a00a4b7d6cbdffd6272
3
+ size 52429698
checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5a0994869a3c17d6f5e780f986d534845fd8176864f38b1db0c7f0ad69f046
3
+ size 52429698
checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e4cf9367c5d3939e33d94b5b3dd9d9c2ad0daf8ba7e0915dc24bc45df9011a
3
+ size 52429698
checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ef13b9738aa58a8e3908b07be390335815278d018d050c1fb88b8b3948aa47
3
+ size 52429698
checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d6d63d632c2b1948dc3c92b63dda1c457022bfe40110e85b4e0e7869ce8ec3
3
+ size 141558649
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:b67807b28acc3ad203d56afef0c46ad38ed6c6d11466e02c79695ca740942d2c
3
+ size 141558643
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 sha256:8a80c7fa6bb56ab8231523b0c41234930c4219a9322529690f490e4e67c1e184
3
+ size 141558649
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 sha256:98bb0632f67e6b8628e43099c2d614f57a2121b46aaab8a65bd2db83e454e52b
3
+ size 11135
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 sha256:2033848db882d8620074d201eefafed810d91f88b4bef006ab62a08008b7c20e
3
+ size 11162
compiled/043ef3de2405203f7bd3.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4818b91b4f63e22e7bc6e16954b1cef2591897b906d64a03cc7bdd5366540246
3
+ size 14603264
compiled/0a7ed4c30b45af937a34.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d78c9b1de5120b2330127c91ceaa9046342cb87c275580fbfd83e3efc021339
3
+ size 16559104
compiled/808b62be7f2953e68ae6.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb3347b528c9dd564a95e5d0224a19acf4893615eba8a683b6257a134d0759f
3
+ size 13743104
compiled/8eb82f172ecf7451bd42.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a606ba8e02a02ccc9b02474bd3941f8e22833d8a419a5a1455d538d0720c44f2
3
+ size 14132224
compiled/9086e4272d7b57eb390e.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb6d8d13fbd8e087904dfa320bed96793d6de8374d68e7cee2064de1359f299
3
+ size 13661184
compiled/b7d11aba4f1cba2bfcd3.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7049a85e3a167347101edf419e24680d9c9d073b99fbe2016899dbffd4770035
3
+ size 13876224
compiled/de2d44d1c147da9b9efc.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88262abbdb2d4150e8d59a71426ff6e50e2ab9044e82e362c621d7aa4f4c77fe
3
+ size 14971904
compiled/fc06285e6b30438b6252.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f98e5259bdc23cf13801b8e73dc7e710ee4f0a45dcc9f2f256e17fa1106251
3
+ size 18115584
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Llama-2-13b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "neuron": {
17
+ "auto_cast_type": "fp16",
18
+ "batch_size": 1,
19
+ "checkpoint_id": "NousResearch/Llama-2-13b-hf",
20
+ "checkpoint_revision": "b0491461253755d8c60bf22f0d696b9e337c6375",
21
+ "compiler_type": "neuronx-cc",
22
+ "compiler_version": "2.13.66.0+6dfecc895",
23
+ "num_cores": 2,
24
+ "sequence_length": 1024,
25
+ "task": "text-generation"
26
+ },
27
+ "num_attention_heads": 40,
28
+ "num_hidden_layers": 40,
29
+ "num_key_value_heads": 40,
30
+ "pad_token_id": 0,
31
+ "pretraining_tp": 1,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.36.2",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<unk>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }