Hugging Face's logo

NexaAI
/
llama-3.1-8B-intel-npu

llama
Model card Files
xet
Community
zackli4ai commited on
Commit
04afae9
·
verified ·
1 Parent(s): 80f8883

Upload 524 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. config.json +60 -0
  3. decoder_layer_0.blob +3 -0
  4. decoder_layer_1.blob +3 -0
  5. decoder_layer_prefill.blob +3 -0
  6. embedding_post.blob +3 -0
  7. embedding_post_prefill.blob +3 -0
  8. generation_config.json +12 -0
  9. lm_head.blob +3 -0
  10. model_weights/model_0_input_10.bin +3 -0
  11. model_weights/model_0_input_11.bin +3 -0
  12. model_weights/model_0_input_12.bin +3 -0
  13. model_weights/model_0_input_13.bin +3 -0
  14. model_weights/model_0_input_14.bin +3 -0
  15. model_weights/model_0_input_15.bin +3 -0
  16. model_weights/model_0_input_16.bin +3 -0
  17. model_weights/model_0_input_17.bin +3 -0
  18. model_weights/model_0_input_18.bin +3 -0
  19. model_weights/model_0_input_3.bin +3 -0
  20. model_weights/model_0_input_4.bin +3 -0
  21. model_weights/model_0_input_5.bin +3 -0
  22. model_weights/model_0_input_6.bin +3 -0
  23. model_weights/model_0_input_7.bin +3 -0
  24. model_weights/model_0_input_8.bin +3 -0
  25. model_weights/model_0_input_9.bin +3 -0
  26. model_weights/model_10_input_10.bin +3 -0
  27. model_weights/model_10_input_11.bin +3 -0
  28. model_weights/model_10_input_12.bin +3 -0
  29. model_weights/model_10_input_13.bin +3 -0
  30. model_weights/model_10_input_14.bin +3 -0
  31. model_weights/model_10_input_15.bin +3 -0
  32. model_weights/model_10_input_16.bin +3 -0
  33. model_weights/model_10_input_17.bin +3 -0
  34. model_weights/model_10_input_18.bin +3 -0
  35. model_weights/model_10_input_3.bin +3 -0
  36. model_weights/model_10_input_4.bin +3 -0
  37. model_weights/model_10_input_5.bin +3 -0
  38. model_weights/model_10_input_6.bin +3 -0
  39. model_weights/model_10_input_7.bin +3 -0
  40. model_weights/model_10_input_8.bin +3 -0
  41. model_weights/model_10_input_9.bin +3 -0
  42. model_weights/model_11_input_10.bin +3 -0
  43. model_weights/model_11_input_11.bin +3 -0
  44. model_weights/model_11_input_12.bin +3 -0
  45. model_weights/model_11_input_13.bin +3 -0
  46. model_weights/model_11_input_14.bin +3 -0
  47. model_weights/model_11_input_15.bin +3 -0
  48. model_weights/model_11_input_16.bin +3 -0
  49. model_weights/model_11_input_17.bin +3 -0
  50. model_weights/model_11_input_18.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ decoder_layer_0.blob filter=lfs diff=lfs merge=lfs -text
37
+ decoder_layer_1.blob filter=lfs diff=lfs merge=lfs -text
38
+ decoder_layer_prefill.blob filter=lfs diff=lfs merge=lfs -text
39
+ embedding_post_prefill.blob filter=lfs diff=lfs merge=lfs -text
40
+ embedding_post.blob filter=lfs diff=lfs merge=lfs -text
41
+ lm_head.blob filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "asym": false,
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bigdl_transformers_low_bit": "sym_int4_rtn",
10
+ "bos_token_id": 128000,
11
+ "const_parameter": true,
12
+ "cos_sin_input": false,
13
+ "embedding_post": false,
14
+ "eos_token_id": [
15
+ 128001,
16
+ 128008,
17
+ 128009
18
+ ],
19
+ "fused_layers": 2,
20
+ "group_size": 0,
21
+ "head_dim": 128,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 4096,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 14336,
26
+ "kv_len": 1023,
27
+ "lm_head_low_bit": "sym_int4_rtn",
28
+ "max_position_embeddings": 131072,
29
+ "max_prompt_len": 512,
30
+ "mixed_precision": false,
31
+ "mlp_bias": false,
32
+ "model_type": "llama",
33
+ "n_splits_down_proj": 1,
34
+ "n_splits_linear": 1,
35
+ "num_attention_heads": 32,
36
+ "num_head": 32,
37
+ "num_hidden_layers": 32,
38
+ "num_key_value_heads": 8,
39
+ "optimize_model": true,
40
+ "pretraining_tp": 1,
41
+ "qkv_bias": false,
42
+ "rms_norm_eps": 1e-05,
43
+ "rope_scaling": {
44
+ "factor": 8.0,
45
+ "high_freq_factor": 4.0,
46
+ "low_freq_factor": 1.0,
47
+ "original_max_position_embeddings": 8192,
48
+ "rope_type": "llama3"
49
+ },
50
+ "rope_theta": 500000.0,
51
+ "tie_word_embeddings": false,
52
+ "torch_dtype": "float16",
53
+ "transformers_version": "4.45.0",
54
+ "transpose_value_cache": true,
55
+ "use_cache": true,
56
+ "use_prefill_sdp": true,
57
+ "vocab_size": 128256,
58
+ "weight_idx": 5,
59
+ "weight_num": 7
60
+ }
decoder_layer_0.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35a6d4afa350c008343364c2f77bf3b9248d338fef348cd752df89e71990176
3
+ size 22864832
decoder_layer_1.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac28f07adc28700d59ae4fa9847cfda3887dfe73893625569f9b0bd78ec436a1
3
+ size 22864832
decoder_layer_prefill.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179b469f9c3d690f134cffc0c9f258b98b9a3396e5b44956c803355401bac9a8
3
+ size 43595920
embedding_post.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe554f00c3cb598bacc9482b7ce8be88f4ed7efe0aae99eae84dfdbb39881f6
3
+ size 167456
embedding_post_prefill.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6658a859370a7d1879713b12974554e72254c293dd05b3f2df4d8d3406bd0ca
3
+ size 196552
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.0"
12
+ }
lm_head.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b9244f16f68a39a8873ea82b2a8f1205abd92a86fc91da9f83f0343753bfb6
3
+ size 3378368
model_weights/model_0_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a08e02fab4af9d28cb27c18a4f5c3faad8252d6fb93b9eabd5c99fcec43520
3
+ size 2048
model_weights/model_0_input_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6206d885db11f08f3bea03f764ef155d6c183bc13b14c2e8a8bbdde9c1d9dc6
3
+ size 8388608
model_weights/model_0_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c486d98ffc5e86b879d261ddc164fe02f1d6d7bb3fbb6800a198bfbc5a2a8bc
3
+ size 8192
model_weights/model_0_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f07a77799d44ce6031f26bd33b7854c57418c7e070fa08d79ab92b9e1562676
3
+ size 29360128
model_weights/model_0_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d799a47e4d439a54488f86e90e72c29db5365de81ce08ea3abf77b7c3a80af
3
+ size 28672
model_weights/model_0_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721b8fd205affbe0ceaf35cd969d974087605e7af5311a8109495efbebf0e7d0
3
+ size 29360128
model_weights/model_0_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16509da277695544d8326306b07bd54de9ab663433c48c1fcf6c6537aabbff9
3
+ size 28672
model_weights/model_0_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2917ef7e4f9e5bfca4c190eeddcd6f04da22354cc229cd06f7d508f0e35a08d0
3
+ size 29360128
model_weights/model_0_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7fefa61845477822f675bfc42ec2247ea50449659a5ba7373aa8b5339c1c36
3
+ size 8192
model_weights/model_0_input_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5549757c42e42585bde6e6a28b18542bc9dbfe554fb6e038d68499b10eb2707
3
+ size 8192
model_weights/model_0_input_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d01bf48144f45955eff9aa36e957e62866ef32f76752de0f044e5322edb59b
3
+ size 8192
model_weights/model_0_input_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21196068e33ebe94b5a3cc0bdce6d24cc15678911cd639794929b96999a6f3e3
3
+ size 8388608
model_weights/model_0_input_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31594f9ac475dac411951579614319777ac88e6f498181e50e7cd4c168532da7
3
+ size 8192
model_weights/model_0_input_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0aa36061041b625aa1fca2869e40cd11281c52aaa37b542f9ec4affccf123c1
3
+ size 2097152
model_weights/model_0_input_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b45c897a03f3e8f4344e9a13bfd330e625c11add955e903b67a02560f335cac
3
+ size 2048
model_weights/model_0_input_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814331a6a596bb9119bcfeeeb9bd927a201b0ea8c007c32dd5ce0597a21e95f3
3
+ size 2097152
model_weights/model_10_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e995053bdb1053f90cd9ef00b4d045c25b743aea800c031f689eeaa7f85cfad
3
+ size 2048
model_weights/model_10_input_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72dfd207a8574ef4e9c8a124a64091c6ae562ce833135a53c8c256242fd9a26
3
+ size 8388608
model_weights/model_10_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd024f6a2b4a85121606e3ed0ddbbc0b393b9577512b6630caa64b05ebe0503
3
+ size 8192
model_weights/model_10_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe5408735eb5650d3c1ccc209f537d797f817b1262435d8b0143dc375dec4a4
3
+ size 29360128
model_weights/model_10_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9be89c1a0ebbbcce5a9e1ca755f493a6d0e97f6e89a0a200232ab7791c459a2
3
+ size 28672
model_weights/model_10_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691d4485ab036b5b9de08ff603e063f1794931979046f356dbbb450df7b608fb
3
+ size 29360128
model_weights/model_10_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fff5a2e8ea1265a44fbf3e73ea855b310590a492e96e9d6315d8a395a753b5e
3
+ size 28672
model_weights/model_10_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b36aecb33b9d952fc3d253a5415bacbf42fb1e862623a3d3ec8ba6c3b1a35d6
3
+ size 29360128
model_weights/model_10_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9208b1a57cb7fa7eda5c98e1748279eef63f7f18636fbcaebc844c6059ab756f
3
+ size 8192
model_weights/model_10_input_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f6797ac52c135f8e345229d18155dd716ad86ae0d0b00e92e9a2f4aaa5b9ec
3
+ size 8192
model_weights/model_10_input_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35adcb62a4b16e53008df54c65b2732b895a492e2a7be06a6ba96b453ac19fbe
3
+ size 8192
model_weights/model_10_input_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcb7dca314885ed51eb80da19d99f3aa77e67e8423ea587dda58464663821de
3
+ size 8388608
model_weights/model_10_input_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5ea939ad5944040c1a274f4de113f6c2614907a20c0f8063cfbff703d2d607
3
+ size 8192
model_weights/model_10_input_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a50be280e32433691563a103cef086f408521065808a618bed319a4e082db8
3
+ size 2097152
model_weights/model_10_input_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e955b83ba3c81cd683f6d3872bb972476ef62eef2673716d1949ea5f94d933
3
+ size 2048
model_weights/model_10_input_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60772c88880b1f76f68ac415ecac6f6f8a4821003842b1afd13899f89702bba
3
+ size 2097152
model_weights/model_11_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa8cf208027f8928698648dd8d54b56078b81a9ddf9830f692b3d611a1eebe8
3
+ size 2048
model_weights/model_11_input_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b4b4d6a4750f7d3ae3f433504f1a307725c32d2e3cacbe29dd94b7bceea24b
3
+ size 8388608
model_weights/model_11_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642fcad7e4d99c6ddff28d29841852adc6ddd80024ed519c2613874c48faf725
3
+ size 8192
model_weights/model_11_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22904499b0ed00b6e9a5715b894fc831647073df844ae586b620c8b9e82d306
3
+ size 29360128
model_weights/model_11_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3963128eed86482f58979a098a1bfaabcbe38f6091555177874837be7f17838d
3
+ size 28672
model_weights/model_11_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb28d9b09b0c86ebf4678d30cf92f49b0c529da110d3daeae1a325d045afaaf6
3
+ size 29360128
model_weights/model_11_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efde43326704f96f2315af73dda64557aac634ca29ae48ea70dfef751bcfe6eb
3
+ size 28672
model_weights/model_11_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc8a105ad456f492d715631d9985f91e2b57da36b53456a4fae89eb1a699f2c
3
+ size 29360128
model_weights/model_11_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612c855022fad1a1525631cfcb7d5adc30fda11bfc067868d984863f1627d9f1
3
+ size 8192