Hugging Face's logo

aws-neuron
/
Mistral-neuron

Text Generation
Transformers
PyTorch
English
mistral
inferentia2
neuron
text-generation-inference
Model card Files Community
2

Upload folder using huggingface_hub

#1
by jburtoft - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+923
-0
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. 0e72957392b3a5897c20.neff +3 -0
  3. 188bb34b13539c76dd99.neff +3 -0
  4. 97cfc2d8d6c59d12a28f.neff +3 -0
  5. cd15a292fcfa32df7f51.neff +3 -0
  6. config.json +25 -0
  7. generation_config.json +6 -0
  8. pytorch_model.bin/key_to_filename.json +3 -0
  9. pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
  10. pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
  11. pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
  12. pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
  13. pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
  14. pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
  15. pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
  16. pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
  17. pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
  18. pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
  19. pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +3 -0
  20. pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +3 -0
  21. pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
  22. pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
  23. pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
  24. pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
  25. pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
  26. pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
  27. pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight +3 -0
  28. pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight +3 -0
  29. pytorch_model.bin/p116.model.layers.12.input_layernorm.weight +3 -0
  30. pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight +3 -0
  31. pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight +3 -0
  32. pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight +3 -0
  33. pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight +3 -0
  34. pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight +3 -0
  35. pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight +3 -0
  36. pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight +3 -0
  37. pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight +3 -0
  38. pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight +3 -0
  39. pytorch_model.bin/p125.model.layers.13.input_layernorm.weight +3 -0
  40. pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight +3 -0
  41. pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight +3 -0
  42. pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight +3 -0
  43. pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight +3 -0
  44. pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight +3 -0
  45. pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight +3 -0
  46. pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight +3 -0
  47. pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight +3 -0
  48. pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight +3 -0
  49. pytorch_model.bin/p134.model.layers.14.input_layernorm.weight +3 -0
  50. pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ 0e72957392b3a5897c20.neff filter=lfs diff=lfs merge=lfs -text
37
+ 188bb34b13539c76dd99.neff filter=lfs diff=lfs merge=lfs -text
38
+ 97cfc2d8d6c59d12a28f.neff filter=lfs diff=lfs merge=lfs -text
39
+ cd15a292fcfa32df7f51.neff filter=lfs diff=lfs merge=lfs -text
0e72957392b3a5897c20.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b549a81664d600c7ec9d5bc351dcef30a35775f16cf33df06a78aa60bb6edb
3
+ size 9688064
188bb34b13539c76dd99.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172d12e12470522562645e4c4ff9d1021a433ac9356a642d5a6984dfa6237d73
3
+ size 8592384
97cfc2d8d6c59d12a28f.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9940b833a836c604a4ba0ff55427089c8681994afb3cad7f841f25c4264e15bb
3
+ size 8530944
cd15a292fcfa32df7f51.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22324417523a6b332a4847778aee4096d0320ff810f6bd3fc149247056f16f6
3
+ size 9073664
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
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": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
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": "4.35.0"
6
+ }
pytorch_model.bin/key_to_filename.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825d20f4a18183eff3963e805edd13ef7eb35b0aff7a850e8153ca1eeeb37970
3
+ size 26397
pytorch_model.bin/p0.model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fece946a037f1875b65e8b481c243a5eb18deeeb4abb9378b1a12fbf69f6d20
3
+ size 524288789
pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f38324df4de55f8ee2935c344c62fa44551ab73747b6571b29d72a620e409d
3
+ size 67109756
pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71552fc62e605445573da7c03604463a2c047196449ee84c2045cff1d79d46b
3
+ size 67109759
pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec8baad6317aed7da66896ce384bf37a9a780b03c6db1889f38674fd418d1ac
3
+ size 67109765
pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e7cdd33c6a8ed277e01a9cd426a0dfdf2e21b48fbc089853926d41a264b5bc
3
+ size 16778117
pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c3eb5fbbf50940f17af3953f2457f2f241a6b72992805e5a5041af279cc8c0
3
+ size 16778117
pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ea7f34e5567a9e49e7c4662d666db90931f44ee9be8940bd13d62df04b12e2
3
+ size 67109765
pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd936141ee0fe85bcdbdf025731b0bad43bd2c6d28b534d49f6a0930c813dc9
3
+ size 234881916
pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dedb343ca3c4d9cca2a1ec5f7f76aac91e1711106b76cc346057c81cd5c9fc3
3
+ size 234881910
pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb96bdf9378a00e63a6be9dbed2d785154cdd9fcb34a10d822775c356ed827c8
3
+ size 234881916
pytorch_model.bin/p107.model.layers.11.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc88f93271c42494a122857d03368e6b149ea437666041adcbfbda98fb879a4
3
+ size 17282
pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ebda0d8b1f9d8ace310144bec1f62aee85dbe3135f3cd1964f3a748d33a54a
3
+ size 17309
pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb50db117af5c79203580d0883e586bafcff6111a3f361bdd6a2ce7e776308a
3
+ size 67109765
pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259258e7a0d922ca7620dc8af2ab75843384761a0bd83ccc725d9f42f68e5d0c
3
+ size 16778111
pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56ea7f39f20b4c5bb7bcef169a1de98b2fbd9bc51317e91d90194b9b13371ca
3
+ size 16778117
pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3085e8397e9a6880e09666324d6e7bf2d7bbb9651915e7d7f5ba6297b36fd5
3
+ size 16778117
pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e7ffb98aac0ba71632b0dbbff156f23a3719e8ac84f67b902053107fe07a8e
3
+ size 67109765
pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a785f23db614522b2167cf41f019aaa3704c3cfc002ed3aa1fb5d0c4fd6e5e1f
3
+ size 234881916
pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadd92e6355c9c2f4eb5ebd633bec4c74242c370f306ae16149ea46aaac68f35
3
+ size 234881910
pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1bbc55083cd7c7732c9221263b36b77aef795cb4243c2b073437ef706985ab
3
+ size 234881916
pytorch_model.bin/p116.model.layers.12.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f881aeb8485027090bcaefb4c03ff5896639745a7b97e38cfaae94751bdd2139
3
+ size 17282
pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7df644a404ab468910f051b564e0bcce1f6fb36242d92579d2a7d7e425b460d
3
+ size 17309
pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53f7d641dd1751356ce3d6b41945e58fa05ea0fc8b52b914942203fc1f901ad
3
+ size 67109765
pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77de0c211f8b8ca66ed57238d283d0ff451532e8e2fe14fc48e996b8191c3426
3
+ size 16778117
pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c23f11e6df663d5cd8593557616c770c3003d883d29157664cb108c48acdb88
3
+ size 16778111
pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578cf4f64a492a8cb27bf1069accddb68e7403143def15c66b4a5828d5187165
3
+ size 16778117
pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044674f18267c4243e49b849f0144f652a5f634331f5f84bea2841899a20405d
3
+ size 67109765
pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a6410bfb512bd41a2bd77d9e97af71e1f1e2215af851d56b0dfcd0a6ac213d
3
+ size 234881916
pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9b832c494b1565b02907ef2ab646fcda1d22b890c5c17d284318eecf980a82
3
+ size 234881910
pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b41b4bbdfa27f1e4610fff6c7479bf34ee83c9d7cecce088721e770f59e00db
3
+ size 234881916
pytorch_model.bin/p125.model.layers.13.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca452ddba55968dc8178f804b22a66a3e0671a4522f7827cb3f780a6f0a06ef9
3
+ size 17282
pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c85f6dec02423e682c65eaec188843147e8b781f1aaa9ad9328d27ec38b258
3
+ size 17309
pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a217e37b4620aee88423fb13bda6b9d386f5d3975fb1b0364866a435ff54ce
3
+ size 67109765
pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9ce0c56e6db46d98ead9e421e8446bd13dc6752c8b578076857dbf6aa09c8a
3
+ size 16778117
pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2587c54ce24ce5b2b7abe43be5d69f2bc235785f35a1c9c5bf930ed13a9b7c69
3
+ size 16778117
pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605a356d1cb9a03e5d27d7c9af7d4525d4752e2b7c2156f41ea3c12a49b442c3
3
+ size 67109759
pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb475fcb012508d2caa09109c5cceffc6d32a2dc10746e5042fb98a377925a8c
3
+ size 67109765
pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a4a4ba1e207ceacb9297b751f12e67abed2791669d896dd4986983ecf5cd58
3
+ size 234881916
pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f96731920a93fa27bd7a7313aadddad810307f33d455c9f2ccebb2102ab8d3
3
+ size 234881910
pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecc74d181354e5f6dc3f854a78eabed9db77cd2dc32a53cb79b6feaa566ff9a
3
+ size 234881916
pytorch_model.bin/p134.model.layers.14.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f79fc4e572a39a39ebcf2322b9020629d39deae74299f0c63cd828cd3bc139
3
+ size 17282
pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62eede7347abe4a886c313aac47f19006ce9821ff1e6a17326c179c19146ceb
3
+ size 17309