Hugging Face's logo

NexaAI
/
llama3.2-3B-intel-npu

llama
Model card Files
xet
Community
zackli4ai commited on
Commit
3884273
·
verified ·
1 Parent(s): a44bbf9

Upload 460 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": ".\\llama3_2_torch\\",
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": true,
13
+ "embedding_post": true,
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": 3072,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 8192,
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": 24,
36
+ "num_head": 24,
37
+ "num_hidden_layers": 28,
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": 32.0,
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": true,
52
+ "torch_dtype": "float16",
53
+ "transformers_version": "4.45.0",
54
+ "transpose_value_cache": true,
55
+ "use_cache": true,
56
+ "use_prefill_sdp": false,
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 sha256:93045978d36c5fd0aa332d61876fc6697e26d5fd66176db7f3bb31201fc20b7f
3
+ size 20718112
decoder_layer_1.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc1b6485304f763b03b9389e0bd295a338c1f17cb627a0894663e5e7b95bdef9
3
+ size 20718112
decoder_layer_prefill.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54fa604782f34c47bcd9ac222f8c2691b3e92aa2c8b9bb5eb97659675d82728
3
+ size 6962232
embedding_post.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad5f0c89ab2ffd9f8ecd2ce8ac92d25f94b248f16019bec8cf627febadc79a7
3
+ size 167456
embedding_post_prefill.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d4e0b6b9334981edbbed1712f40ae970a9407faf67603cf80646cda77635c56
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 sha256:5c99956df0b448d88993229e8420e308ba52de4ad6b3870b22db2c48c0d5c37b
3
+ size 3208736
model_weights/model_0_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b5b914708586df0f2712f0b25d88d473f7d22486e02db3edcd0278cf0b1889
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 sha256:139adc3306e0c52ca61902b15ccaeeb9c3d930a16e5b25b0af1bbf8453af44a6
3
+ size 4718592
model_weights/model_0_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a353d79a5668ec5ddbc7c393f9d7b9be02fdb1b85c0f1d35557d1203efacd41
3
+ size 6144
model_weights/model_0_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdf6ae299f26dc206567b28a002198fca24321594baf67fd2028b87ad069a76
3
+ size 12582912
model_weights/model_0_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2831f932f7989f804c6a12c9545499a9151564589cb6fa25b9fc4fc677cfedda
3
+ size 16384
model_weights/model_0_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0be9e99c4c0e7a5a1bac4fae31218b2d09b1950e9c23fc1f5c0fdbc367e1441
3
+ size 12582912
model_weights/model_0_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:682bd53feaa7b4e685243c207b4e7c82f00a0ea73e3aee58ff70deb3a015772c
3
+ size 16384
model_weights/model_0_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a619539dfadc25bc472f841d6ff7bc34153c155ba09c95524d3b391034d36d
3
+ size 12582912
model_weights/model_0_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c3306b14798e601857348ecccef782bc15450282b7984c43dab38e93176969
3
+ size 6144
model_weights/model_0_input_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0671d8252470d4c99b538827e7151eacba0cb273414965ba25699732cd957f
3
+ size 6144
model_weights/model_0_input_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d49848a21d3d39a5bf67ae3972772b71b82f2ea386ddec879df0433cadaf39
3
+ size 6144
model_weights/model_0_input_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc8c38191f1fa4b8feea306a7126b95d81013e58e0e1585411b790da01965a9
3
+ size 4718592
model_weights/model_0_input_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a259f8494465647df015801ec2f98321095802813a875ddb7a56118c17770ebd
3
+ size 6144
model_weights/model_0_input_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55d024febbdcb32ff6377567c549f8ac7cb1a84c49b7bfc67259531dcab0214
3
+ size 1572864
model_weights/model_0_input_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e9ed7493223b373478ac9c1b94354a77a24a52d2b697ee86801bc517435e37
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 sha256:8a645e43f21c409a38e91d3426a191aebda7499e8b9d6f3c41be6af4cba670fd
3
+ size 1572864
model_weights/model_10_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79b457b25566ff1c7b6a68cc94b3dfc63cf25dace7d653d27c93f64083046c8
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 sha256:402ccf3c26b0cb4e000e8c54f5ae01328f8ec08bdcc08ffa9c481a0bd6422242
3
+ size 4718592
model_weights/model_10_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e30c94502ccc35d7b1a32846f97436a8718f4be85d8a9707042c9ccc0a545c
3
+ size 6144
model_weights/model_10_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e8371c048d6171877b5c91563e069801d2f67248bc75a548308752cb5053d6
3
+ size 12582912
model_weights/model_10_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984ce1975bdd9c99c122de4a3329e5494214a324fbd03bbbde9db93bda297e0e
3
+ size 16384
model_weights/model_10_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc894cfa670dbdda5d59082d67c0508bc1df501fd1bea93a0d73bc9cffa6e018
3
+ size 12582912
model_weights/model_10_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53aadc8791b1e5a9191f60c77a04040a43cf8aaa4678abbb38820ed64ce0bdd1
3
+ size 16384
model_weights/model_10_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce6c4ebf41ef25906e637fad0910d6a4903aa1cae7d60a66f1ad3b01484514f
3
+ size 12582912
model_weights/model_10_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f618fa5f81d6d60a6629034c7369c817253448fa51a24aa3aa7ccd52da3bf46
3
+ size 6144
model_weights/model_10_input_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6d17559e9318069af4a97e8788fcc9fd343514427435587ea47dfdd7a87a06
3
+ size 6144
model_weights/model_10_input_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d81b71ccc214f9e5a367992e87ad757b2ffe7e7e0426388fd8d7eb90b40c7b
3
+ size 6144
model_weights/model_10_input_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa30a7f9e9b28c406550a20e08d4b648507992f1c2125d80b03d20c67bf39c6
3
+ size 4718592
model_weights/model_10_input_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb85bf460ffda898b6075778ecdfaa43dbed685102123da3e010935eaa0e7a80
3
+ size 6144
model_weights/model_10_input_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688691709c635f6af9a1a38ed998e405ddc2f8e33ec9c173b4abbf41bc26d1fa
3
+ size 1572864
model_weights/model_10_input_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c834d03267eb054363b1e4ea34140a089cb7a653c6596736df7c35900354fb
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:c7c8720043d9a3a502975da8a7764fc412294db411f53ef7dcb2daaba7c02f6b
3
+ size 1572864
model_weights/model_11_input_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4571ceca001d64c7ab06b93d5ac13a0cbdc3cd0c946d6670d155a8c6e25431b7
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 sha256:3e92fad61cf18f9b74af70f9626256068b428e14afd7f997d07413890e748002
3
+ size 4718592
model_weights/model_11_input_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521622e2d49043c6ee76d264b489d145f5787563dc854ddc2663c682615b813d
3
+ size 6144
model_weights/model_11_input_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce5493502ead9a28eab0201130043556b930161221ea2e9d1f538f831c706c7
3
+ size 12582912
model_weights/model_11_input_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d14d58a36853f38c40d967100cb35e6c1c9d8ca55771e4cd3adc8776d94d692
3
+ size 16384
model_weights/model_11_input_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21c0aa3d346f09237c85a0a8f3a1b438fe7c843c6d01ed1a33d42b3915c6faa
3
+ size 12582912
model_weights/model_11_input_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439fe76aa813f86ba941efda06b077f13c87cbbce308fc476081c97e119788d3
3
+ size 16384
model_weights/model_11_input_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d083f4c95846175cebaf278ad90b164465f3242891c376e39ce7338b063408a
3
+ size 12582912
model_weights/model_11_input_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b43e6f98083e490b006bb8b1716d801e4f711230d6b1b068f5c901ba05d08f
3
+ size 6144