Hugging Face's logo

jburtoft
/
TencentARC-LLaMA-Pro-8B-Neuron

Text Generation
Transformers
llama
Model card Files
xet
Community
1
jburtoft commited on
Commit
d2e7531
·
1 Parent(s): 6b0538c

3ba20f20e25ab0cb1a77af05f901908b55c2641d3fda1c657f4dade66b1ce7c7

Browse files
Files changed (24) hide show
  1. .gitattributes +10 -0
  2. checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight +3 -0
  3. checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight +3 -0
  4. checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight +3 -0
  5. checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +3 -0
  6. checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
  7. checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +3 -0
  8. checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +3 -0
  9. compiled/1578fdad18474e7664e9.neff +3 -0
  10. compiled/6eada744f92fa0ae0159.neff +3 -0
  11. compiled/79d794ba6f842ad3d39b.neff +3 -0
  12. compiled/7d8bed0b51da3d23d956.neff +3 -0
  13. compiled/7dce96f723e4f83a27b9.neff +3 -0
  14. compiled/8c17baa78ef5d04bfa59.neff +3 -0
  15. compiled/c51924b750f5e217b31c.neff +3 -0
  16. compiled/d6aad471c42a37bc3ced.neff +3 -0
  17. compiled/dde77a9416ad07853677.neff +3 -0
  18. compiled/ebc145ac6be502643b10.neff +3 -0
  19. config.json +36 -0
  20. generation_config.json +10 -0
  21. special_tokens_map.json +30 -0
  22. tokenizer.json +0 -0
  23. tokenizer.model +3 -0
  24. tokenizer_config.json +42 -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/1578fdad18474e7664e9.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/6eada744f92fa0ae0159.neff filter=lfs diff=lfs merge=lfs -text
38
+ compiled/79d794ba6f842ad3d39b.neff filter=lfs diff=lfs merge=lfs -text
39
+ compiled/7d8bed0b51da3d23d956.neff filter=lfs diff=lfs merge=lfs -text
40
+ compiled/7dce96f723e4f83a27b9.neff filter=lfs diff=lfs merge=lfs -text
41
+ compiled/8c17baa78ef5d04bfa59.neff filter=lfs diff=lfs merge=lfs -text
42
+ compiled/c51924b750f5e217b31c.neff filter=lfs diff=lfs merge=lfs -text
43
+ compiled/d6aad471c42a37bc3ced.neff filter=lfs diff=lfs merge=lfs -text
44
+ compiled/dde77a9416ad07853677.neff filter=lfs diff=lfs merge=lfs -text
45
+ compiled/ebc145ac6be502643b10.neff filter=lfs diff=lfs merge=lfs -text
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:cc267f7ac96c59779af19ea0aedc4ff70e0d4f6a3783d5aa91c0ca5fcc1583d7
3
+ size 67109762
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 sha256:1ce5b53cfd9c2e2ac3e19d516fbf10667f46773bfc5dae9689c332f088b0d834
3
+ size 67109762
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 sha256:8de438597e310032232881137dcb9627f942ae1660eab3b487a3045792222c10
3
+ size 180355961
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 sha256:46696e92539736625a1d05c289ddeed066f001c8b4e71efc6cfe3293cbd78a4c
3
+ size 180355955
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 sha256:7c8bc781e19143075e79ed9a4689739d37332a3ac635992aa59a985576ce645a
3
+ size 180355961
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:bc9ab47d576e72c07a8fa6b1d82066bf01eb41dbd9daddbea2871d96ff2e1430
3
+ size 17279
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 sha256:088c18c913787770abe3f18e31ee7626c22aa27ef5b1c18b543fd94a5c464b9d
3
+ size 17306
compiled/1578fdad18474e7664e9.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fa0eaf2b5eec5063b8847f62156e5219a644a4fa6fc35b9465ae12bf47089e
3
+ size 16446464
compiled/6eada744f92fa0ae0159.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a659dab6e50f054508ab2e2d76e3ca4469bf7b0724593e4cc7b50aac90793a
3
+ size 17583104
compiled/79d794ba6f842ad3d39b.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d0ecc23cc5a369b0bae4f8461d7c41ed66b0aebb8dc2e169bdf304b00530d6
3
+ size 19067904
compiled/7d8bed0b51da3d23d956.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38396389ad23292c2c1d83a387d94c1185ac53b3e9ea7f9a2eeef379a595faee
3
+ size 23798784
compiled/7dce96f723e4f83a27b9.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f263d3e18a5ae3f0c81f92992dbddd21da42c075af7e68b835cdac1358e8192b
3
+ size 99841024
compiled/8c17baa78ef5d04bfa59.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2db98ae21f84dbc87c1fa7f7fe1a6b40d6abb34a9e1da3e0f2e1930fefa079
3
+ size 16149504
compiled/c51924b750f5e217b31c.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f9dc12248fd4c413130deb89661532ac9ece1f640f0b690d23bcd5534934a6
3
+ size 16825344
compiled/d6aad471c42a37bc3ced.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f64b34a46df761a7ae1beefdc666ccce7c4883dba910888a595c8c0086575a
3
+ size 16774144
compiled/dde77a9416ad07853677.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f13ae11c6da7976ad87cfb7030ee5e1d26f5e36563800e8750f63a3a7967b4
3
+ size 36393984
compiled/ebc145ac6be502643b10.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3a9e524fe9935a61e21a4eb76b9d657eb473336e15e70e5a0c640b06324ccc
3
+ size 17941504
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TencentARC/LLaMA-Pro-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "neuron": {
16
+ "auto_cast_type": "fp16",
17
+ "batch_size": 2,
18
+ "compiler_type": "neuronx-cc",
19
+ "compiler_version": "2.11.0.34+c5231f848",
20
+ "num_cores": 2,
21
+ "sequence_length": 2048,
22
+ "task": "text-generation"
23
+ },
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 40,
26
+ "num_key_value_heads": 32,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.35.0",
34
+ "use_cache": false,
35
+ "vocab_size": 32000
36
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.35.0"
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
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": false,
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
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": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }