Hugging Face's logo

enghwa
/
neuron-mistral7bv0.2

Text Generation
PyTorch
Safetensors
mistral
finetuned
conversational
Model card Files
xet
enghwa commited on
Commit
2723e74
·
verified ·
1 Parent(s): ff52fd8

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. -split/config.json +27 -0
  2. -split/generation_config.json +6 -0
  3. -split/pytorch_model.bin/key_to_filename.json +3 -0
  4. -split/pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
  5. -split/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
  6. -split/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
  7. -split/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
  8. -split/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
  9. -split/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
  10. -split/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
  11. -split/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
  12. -split/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
  13. -split/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
  14. -split/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +3 -0
  15. -split/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +3 -0
  16. -split/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
  17. -split/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
  18. -split/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
  19. -split/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
  20. -split/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
  21. -split/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
  22. -split/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight +3 -0
  23. -split/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight +3 -0
  24. -split/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight +3 -0
  25. -split/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight +3 -0
  26. -split/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight +3 -0
  27. -split/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight +3 -0
  28. -split/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight +3 -0
  29. -split/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight +3 -0
  30. -split/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight +3 -0
  31. -split/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight +3 -0
  32. -split/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight +3 -0
  33. -split/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight +3 -0
  34. -split/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight +3 -0
  35. -split/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight +3 -0
  36. -split/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight +3 -0
  37. -split/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight +3 -0
  38. -split/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight +3 -0
  39. -split/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight +3 -0
  40. -split/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight +3 -0
  41. -split/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight +3 -0
  42. -split/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight +3 -0
  43. -split/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight +3 -0
  44. -split/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight +3 -0
  45. -split/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight +3 -0
  46. -split/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight +3 -0
  47. -split/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight +3 -0
  48. -split/pytorch_model.bin/p138.model.layers.15.self_attn.v_proj.weight +3 -0
  49. -split/pytorch_model.bin/p139.model.layers.15.self_attn.o_proj.weight +3 -0
  50. -split/pytorch_model.bin/p14.model.layers.1.mlp.gate_proj.weight +3 -0
-split/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./Mistral-7B-Instruct-v0.2/",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.43.1",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
-split/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": "4.43.1"
6
+ }
-split/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
-split/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:c79cc9fdda70443f46bcc7318afd0070f238ee378218128fc6b31ecd8f3a7f41
3
+ size 524289250
-split/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:dbcd86bb7ed7b202c1f46d41578a154b58df0ab2a6aecadacc6564164933fbe6
3
+ size 67110243
-split/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:d40a9cbab0d5116c8f03e418b4f35cd313fd1f50348ad2e0c29a22749a607568
3
+ size 67110248
-split/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:c9cbec887bd75aaf3c8f8d4605fbbc131db11961e01e0240fb3d8c3fcf363f13
3
+ size 67110322
-split/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:d90aed92602153f6e52ecb21e1698cccfabd14f2d273db91bf4f8ac9fae45d74
3
+ size 16778674
-split/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:ef95e3ea24fd6601ad3a66bc6ead7bec9da24bc64e7600051d61792c1584568d
3
+ size 16778674
-split/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:f2e0d46867192c85b6b56ee8f0b193f33913bd0fd1c02df25a152b3700d1cf48
3
+ size 67110322
-split/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 sha256:593b36e861656dce695d5fd04fdc7ac8b4944a2498e38eab0e82a092c1824fcd
3
+ size 234882403
-split/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 sha256:7b138e27843acd67bfc927a5e13b8737b4eb7460405207b9404b417c85bfab75
3
+ size 234882393
-split/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 sha256:99317c85cc7688fbddc9803f3e4315e3dbd5a73a35ffb0ea5c675abb0f49178f
3
+ size 234882403
-split/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:f77d441b687e91d1e600507abc8e4296730ce1706af3dfa00331c8fce94aa1a5
3
+ size 17773
-split/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 sha256:32473dc1d1acf2ff25fe2a9cee09a1e84cf15018e4e20237fd8a919851e14ebd
3
+ size 17882
-split/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 sha256:800b3075cdb4316a1f3c593e39ed2e7c0d97c49db53889105837e75cc1a676e1
3
+ size 67110322
-split/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 sha256:17cda24f952a74b88c42b138025e951b1d79b259cb662a82e19b890cf0d3f3c4
3
+ size 16778600
-split/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 sha256:9f39e983bf6f85e494a79ba20cf45da44d70482babbce9d46d008469d9dab815
3
+ size 16778674
-split/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 sha256:8cd33d131de96bc826705ba470b31b4528cdb1daa9ad4a923e8279050b9952c4
3
+ size 16778674
-split/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 sha256:9faeb6396aa2745171a53a1d9552f149c8626f27065024607c07d85376fc1d7a
3
+ size 67110322
-split/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 sha256:6d1c432389ca99ad3aaf8654e13995ca955f2df42fa02998b5b0696fe08968ba
3
+ size 234882403
-split/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 sha256:28212e022336aff7abb48dee240ad55a1482759ada1828746fa131174e626409
3
+ size 234882393
-split/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:b1806c3cec788939f133f22b8a9e515449f6bdd2ca21a33d234da53899d73388
3
+ size 234882403
-split/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 sha256:29fddacc2747f262c152b850ef877dd8144820f72f638695bc71215c997b8946
3
+ size 17773
-split/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:a8007805401f4d644e97a26dd7b2421fc586e24dea3e2bbe05dd0f26e9f79372
3
+ size 17882
-split/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:cf48be35dda343eb6d9c2819024725861a8c3e84aaf74dc830ecb81de421ea71
3
+ size 67110322
-split/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 sha256:71467ccad2019138a09eee5a93fa88bd58e778428944e12471420cc52f2ac30b
3
+ size 16778674
-split/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 sha256:6dc6fef1b14659f5a5947166b3a4011ba2be0d006ba9337d86f91990ec28e0ec
3
+ size 16778600
-split/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 sha256:9939a71b347435ec77249abcdc3249f112073fb54b4b33aecb67627805a8202c
3
+ size 16778674
-split/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 sha256:705e447d01959b9ebc25bbf1d8ea30275cfadace50aebee23799ae67dc609a92
3
+ size 67110322
-split/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:b074b885b0cd15273a26d0abf1ef9ef80cc325e1cce6d167e8357f95fe9a1c81
3
+ size 234882403
-split/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 sha256:9b1c6a6d61ee131c5aeb996cf25e8083709e48e1c6633eab051d1e1d76ba8e14
3
+ size 234882393
-split/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 sha256:3ad8a64fed792c52f603846d31ee01e8f6acb71e96b185e51e499aef84f1279a
3
+ size 234882403
-split/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 sha256:17944abd24a1ebaf6a70c024e9ff0e570d725e82c65f1ea9c478ddd9be1ae646
3
+ size 17773
-split/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 sha256:5dba1a88b2d2726bd7bff0bae18c68a4c7b5284b13ec7565dc8cda9c770312e5
3
+ size 17882
-split/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:dfc33d73fcf28fff959a9a9e140ea98f8887e85052b88fa9c1aa2934c8fd48f5
3
+ size 67110322
-split/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 sha256:4eb291c00e0151cd22fb7f01a1ea002fd77e163e4aae8d19ba7454e1fd81dc29
3
+ size 16778674
-split/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:a62a6f6c02d34484f4b2fa13e2cb7f23478e9704e3e2745330e87948c60c9d4f
3
+ size 16778674
-split/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 sha256:481aef450ebe0f261635e3eb324602506e5626f4ae7937b001c882ceabac64e5
3
+ size 67110248
-split/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 sha256:3a9feedc6474312df64cce1858004642f3ceee83c293162e7ee0fb5706a9b220
3
+ size 67110322
-split/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 sha256:1fcd98cfbd14e994cade668747fcaea3624f2bfc3283a8fb7e67372505aa0614
3
+ size 234882403
-split/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:cc0e6806e1cc5f21aac6decb6527ed4e3b895ddb79550c23b6f9363a29112b64
3
+ size 234882393
-split/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 sha256:4e8e63c69841c6f65b5ef9ff91d7fd9b123d2f36504c1f739cb3e6180233f8a8
3
+ size 234882403
-split/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:d7a1464c1e74b677529f5f60f4bf7b82775084b1950a7d0d0bc077896d08d09e
3
+ size 17773
-split/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 sha256:0cc82c5016809c66e20346e3335632a121e25a4604e8aa3db0daa22facb60bd1
3
+ size 17882
-split/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa36b49d8e6d615c1e619f26f56f11cac667758737151a8edd5e86f05dda281d
3
+ size 67110322
-split/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfbd8b53e17fdc6b5a9a81a0644aabe27fe91b3e67a608aba4a87d96ae58912b
3
+ size 16778674
-split/pytorch_model.bin/p138.model.layers.15.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d22b8841b1c1f206b25a735a5a29e4b81641364fc7dd5cd287982b46b6bf37
3
+ size 16778674
-split/pytorch_model.bin/p139.model.layers.15.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147e7dce6b478ef7a3e3fcc8625555238d256fe01c952695cf0ff8eb84bb772b
3
+ size 67110322
-split/pytorch_model.bin/p14.model.layers.1.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f552c2421c3d6f8cad66983e9e2fc5adb8e5832acbdbcc63d8d17584163ee8fa
3
+ size 234882393