Hugging Face's logo

enghwa
/
lab

Safetensors
mistral
Model card Files
enghwa commited on
Commit
6fe74ef
•
1 Parent(s): 6a625ec

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-v0.3/",
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": 32768
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 sha256:6d435d4464e8da6f0264f8b19ab70d7f3d35eef7df4594e3b34d52dcbd517904
3
+ size 536872162
-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:f88fdd2b68d26fcfe7959b2b58b9ea31ec16963fb36459c616d2d6ca2754ffb1
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:e374061b2dcff0797830be242a558dce0850c960bcb67b5e62075736007b12c0
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 sha256:48384dce123907336e180ef9979b0952b8bef014101de6fd7033657c3674011b
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 sha256:4a59481620b6f6bc145eb6a61527fafa4a168bd9d2c1998527e12de1fbca631d
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 sha256:86bfb16becb6b4200ccfc7b498a5eb5c74f60eed83caa94b092ac1fc953e110b
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 sha256:604f9a1cec2051425c668644295e2b5b6f0e00c35b123025d5a4fde8d5e13c6d
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 sha256:7a752c75655f43ea006f5a7a9252c79aeb5a8c0ad32e70b5c7b021dbfbd1aaf6
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:d9bffa2dd4bdfdd96e9b357ec000f72d209bdb138061b71a423deba858bf4ae5
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 sha256:0d8adcf237d94552c3e1cba2afad73a8e8ef7ba7e11e3c58056d9c8cd7a26a90
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 sha256:575137c90cffba3d57a12554ab56b8948868f81285c90ca44ac4073b2cd23c9a
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 sha256:55bc915f619352f6685431c34fe04ad7a9dcd571a7a86c05151eee4db440da13
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:a009d073ca2fe9e87ecd0810b8db016721e4e83b1d42c7e8e2f412b7b3530c61
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 sha256:484f9970406da7004e62a180f00c556d8cadd8339d728b3044aa52c3c4d8284f
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 sha256:123f258759c1444e7185ce53fab106257bfb96a95a9b3753cb86732f20530def
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 sha256:52a402da87bed26ebeb1d65b4dc66e2b51b8e229a17f9a1a394156115fc5e3da
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 sha256:4c85194916832dd659fb11db41381f75cade67038fc85c7d5335f23dd4566a41
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:da59dc9e6d043b5daa723bee8261e801a5cc738fee38fb527430ebe8559fb1e6
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:e821c0994408435ee049db686f6df6498db29a82c15a4424ca72c028a2f1149e
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 sha256:08ea0fd59edf0da492acc0664766306705bb4d01c7fd361eaefdcd7ca1a7fbf1
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:f434f6808cac1736c2e384534e2f96b7e3f6faf2c9b49c8ccb5f2e8b1485dc56
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 sha256:372dbd20e0540137607e5ec3d8940ff1cac6dff051c28bdda6f6a1300540069e
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 sha256:0da9f1a5589e5456ee607096a519d403935a9264889b32d44e4535fa2d8b53ef
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:bf7d1792dc12943f2de9bac18ca383df65fbe53accb9442452cb60ffb91d50bd
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 sha256:9777388d28af9cc5b90bd15ca4e3e5f95ca2e8dc2214777d538d897c9bf8a602
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 sha256:076eac0db968f48c7dc3971a3cbc4deda9a86bb7bb0cffa562e2e1cf9ac95555
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 sha256:48c3470d193a8009716268b107c4cae86145467fa7daadd7125476ae223424f0
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 sha256:6caeb3a63e53d31cfb12892b7628638d57b4bbcee407b0adc887ba0a9e6adf4a
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 sha256:01aa1f809c331bf6c78fe72b0f2b093edf3df77f778500b752f59afdebaa080c
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:e3854f25003a072d2a7e8527677af221d47eb270ceee0180bf96f22a248d9583
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:f5502e2384cf518a26b1ba7b193c27ca7455090b711593846f0a75103167d869
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 sha256:1a3500db5a357257671fd58d0f5504eba15c8260eaac9d3295f47efa28584ccc
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 sha256:0a9a821ce30511b5c614ddf350aa5f9ef302a8a2ea0ca13f91f8f4dbecf80eab
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 sha256:1973c23aaed34fb0ae6158d2ab6ddc44a2509fe513a84243d8f074e6ef452f36
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 sha256:84bc970248656594797c473b05c84bd790031dfef763c19ccae3ccb0e1d68ae3
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 sha256:5552f4ee9f36ad40b8c092dd446e2acd3dbea6aaf1100fc5ff48b192753e2f78
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 sha256:180203bd0d156b74d4f07c449ae1cead954f9c7668a359d198a1cf6d0d9630e8
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 sha256:488778a4dcff7c1b99fec5877e879e5822ff7a359501dac9da43188407dff511
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 sha256:19978fd794059246573214e5c51a7dfbf83891b469c10a5995190f2f5efeee44
3
+ size 234882393