Hugging Face's logo

sequelbox
/
Llama2-70B-StellarBright

Text Generation
Transformers
Safetensors
English
llama
stellar-bright
llama-2
llama-2-chat
70b
text-generation-inference
Inference Endpoints
Model card Files
sequelbox commited on
Commit
91b5679
•
1 Parent(s): 1559b64

Upload folder using huggingface_hub (#1)

Browse files

- ba8a4e21375dfcded4376ef2618a29e11c472daf3b05bed651aee8110c0219a5 (bc7e03aede0ceabfac53e57513b41d84d4ff56ee)
- 3027e920ba6ef99ec5b323a8463f224c3f845f58a2716d4be3825a86cf5c1516 (31d97311553bf1a9d2475f7bafbb245ab6ce241f)
- 25c99e9acc3295f3587902bf47a126356836bb59a13bf2bcc03fbbae71b7b8ad (bc68d86f5d1907685289b5b47ac86a1bf2fac502)
- b2d2e3a752c2f6694fa698ead8b654131f673e200c46c09b73d3da80d333678b (e1bf30b7c0a3e73793895f042d31af5ffbe0f882)
- 1781568d6f29a651edb6219f2582f59f3e75e6ebcdc1662b7c035deb7c5a2689 (0051cbd51ebeb681d6c3c361e1663f91accf1f31)
- 8eeb2e17daecd1515aaf887e6043d12a8ac61fd2b0b64dc03963b294f053fb33 (30ce1d9fd70aa55dd7c0d8a9fa49820b37999eed)
- 3a2211506533e514dd5fe00b595e497d0d40063b2bb257e46eb117b1c1b01ed4 (836d34f6a57ea2358d2e20a41225b83f743b3e54)
- 1835d66ca0bea1e8ecb98575d37434a886c4d1534f35593da323747e6fc40761 (524ee05f49fc61e74d605e93b2b7e3b965d03b1f)
- 48340ccde6cb2ddf1e72d4bbf233e8fc63246ff33f898735be588d385344c8c4 (550796be44d6b02c0af76986ad0fb6945786bf17)
- 5085ed9f40bc838d3dbd1a881e710e61d5bb26624e82d3640977919e31e222d1 (53c00b72c45b500d0ca7bc8bd29f1a301b37dcb3)
- eb0ff1fdd2fed575fc6a1c9d1fa1ca5b5d24effa48d1308c3fea7de7f3c67808 (f97cb92ea075018ce88fcba21e3a965b5714c079)
- e720d5e8cf8504dc348f960a7242f859ea28a0662f3606f65eb1fa16fc9f8248 (27a7b47c4b6f25231a18b8e5442faf8bb458da7c)
- c2d991559b4b3f8499aac6b49841e1aeb31c3f5caa146c4177bb5003eec4bf16 (62c3815872d3bd2a599ddca96376611861b5ead2)
- 20649d4bdc604b0b07cdb0b63b989f3f1c0e3bc6c21da888b6a79114f831f4f3 (55e5e593bc49736bf9d206ca7ad90ca9c76e55b5)
- 71e47c58a3dd5d4782cf1e7551c1deb97864a340614202f5cfdb63f7d082d597 (8a9c98755cabacbe81906f41eac65ed3151746da)
- 36a3842ddd8a1fb50bd3be8dca4e405c77b955fe852cf635c7d789f570800dc0 (68720cb3b57a1c463c4b311f76316157a65fc4f7)
- 15a8d5bfeed993fb7d7d0b5efa66d1a33b867c6cad9cbe2ee2576a78251fb78a (0d324a71c30404a531d26d3424f32ebad1429330)
- 3e5c76f16fd957b8fe865795d8b529bd5ea76c018ef549941833d32e6d606379 (d1f54366e0111e125cd28e53845b8678c730381a)
- ddcd14a84786bcdb1d80fac1944c60e8bdaafa9cb48f685d9e3343be9bacb091 (7d3062e73995221145da61448d0be953eab6e9be)
- 8b060c73e872e75a057d482301abc66ccaf9e65768ecb1a72432ad28095e7423 (fd54493f1434dc129382679437073bceb052bc58)
- 7bc7e86d3dd9cf31187c145d571f2e108c00980b58d6f819aace18579d36331b (e16926b829282a518206d41db6968a7b35c922b1)
- b1bef931a248011616ee47bc8bdf977cc5b00e1d84b03d27a775523a080015f1 (f5ce10208b58412990290487003181a3dc32fd77)
- d23c8fab8be46374fdfc4468822a7482b793e213d9c40168b16d25dc30f7651d (0e9840131af51551096d4439c7d5ad33ef44a615)
- c04f8caf853340e666368059281dfba67216bc8f6e10f492b70114e7f89fab29 (f1e066fc8aa4ab6766f75a701419a6af0547ec05)
- 41608aaf7ab6fa9c8ccf075e5bc474f07236beff238a59baf40d9222f081ccbd (efbc686850f547223590d5c9dd5da9c53b44d889)
- 524ff234fbad982ca2d0db6b7f4575a68de510acdc909f4da45d9b3363569f12 (f7467446bc28e2ee2088a5b00689c84bc81b1d4b)
- 073f7c22e6149353522bed30cf7828f8f75a81adb3c3c1ff51caf955f326f627 (fcc4a524f64859a60c3c513abbb2a92684bbe432)
- 362d5d5ffce676578097fa644d6072e1bb4826f8dd9bb4f27e471ed8066880b0 (249667509eb8a155996df4a2a05de31cf413274a)
- 63bc91ee1df6667e0a43a41967a0bd475c2d6b653821e4504741da445fa52957 (aace735f8a35accd92f610bdc0df852a12907c57)
- 2035ef52f7ac31f9adb621cb2113db26308ea2c2425be34dd45d641d0ceda7d0 (ddeb4a4defa20a9cd2a178afe92676e5c1a8c5e9)
- ac37f868862b53d39da8ad06ca97b92cad756ba993a060c752f521b539d3cba2 (c9aac47158ddf337a04e76fa40da35ab8eb00ad0)

Files changed (38) hide show
  1. .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
  2. .ipynb_checkpoints/tokenizer_config-checkpoint.json +38 -0
  3. config.json +28 -0
  4. generation_config.json +8 -0
  5. model-00001-of-00030.safetensors +3 -0
  6. model-00002-of-00030.safetensors +3 -0
  7. model-00003-of-00030.safetensors +3 -0
  8. model-00004-of-00030.safetensors +3 -0
  9. model-00005-of-00030.safetensors +3 -0
  10. model-00006-of-00030.safetensors +3 -0
  11. model-00007-of-00030.safetensors +3 -0
  12. model-00008-of-00030.safetensors +3 -0
  13. model-00009-of-00030.safetensors +3 -0
  14. model-00010-of-00030.safetensors +3 -0
  15. model-00011-of-00030.safetensors +3 -0
  16. model-00012-of-00030.safetensors +3 -0
  17. model-00013-of-00030.safetensors +3 -0
  18. model-00014-of-00030.safetensors +3 -0
  19. model-00015-of-00030.safetensors +3 -0
  20. model-00016-of-00030.safetensors +3 -0
  21. model-00017-of-00030.safetensors +3 -0
  22. model-00018-of-00030.safetensors +3 -0
  23. model-00019-of-00030.safetensors +3 -0
  24. model-00020-of-00030.safetensors +3 -0
  25. model-00021-of-00030.safetensors +3 -0
  26. model-00022-of-00030.safetensors +3 -0
  27. model-00023-of-00030.safetensors +3 -0
  28. model-00024-of-00030.safetensors +3 -0
  29. model-00025-of-00030.safetensors +3 -0
  30. model-00026-of-00030.safetensors +3 -0
  31. model-00027-of-00030.safetensors +3 -0
  32. model-00028-of-00030.safetensors +3 -0
  33. model-00029-of-00030.safetensors +3 -0
  34. model-00030-of-00030.safetensors +3 -0
  35. model.safetensors.index.json +1050 -0
  36. special_tokens_map.json +24 -0
  37. tokenizer.json +0 -0
  38. tokenizer_config.json +38 -0
.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "max_length": 2048,
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "stride": 0,
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "truncation_side": "right",
28
+ "truncation_strategy": "longest_first",
29
+ "unk_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "use_default_system_prompt": true
38
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./new_model",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.34.0",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.34.0",
7
+ "use_cache": false
8
+ }
model-00001-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f27ac306de9c4ceccb6e7362a6949e4ad4feb04436b923cddfa90621fb0bf0e
3
+ size 9476641016
model-00002-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a310484f1e4acca53efc6a38b457844d466b0dfe6f5275b65e1f0607e3c30f43
3
+ size 9367654872
model-00003-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fd8195a13ec86cdda6dc160b50846d04419b621f37af74353f044c34ca2824
3
+ size 9966915560
model-00004-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13113c1ff07bc5cfead4b37c826f37e62af4bac8bdc90b39d0b8b0951a5141ac
3
+ size 9090764688
model-00005-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bced905095c588ffc5fb276925a4884347627cd3832d500a933ac2a0651b22
3
+ size 9367654904
model-00006-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9470121f21f5ca3c65ab0e329e640a9ffb4835d390752fd41303a36e0338b1
3
+ size 9367654912
model-00007-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d143d5e2a5cca37bbc316ddf8b4d3418f02ee8e23d32906b3357f8b4c3ab47d0
3
+ size 9966915592
model-00008-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba099bc64292de82f53fd1a6907f659b1d306c0512222c9ad5f1d74f6ce702f8
3
+ size 9090764696
model-00009-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bd68978ddee9a9ff501dea6bc453aa6c979385fc6a5cff8554f2801bff700d
3
+ size 9367654904
model-00010-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f991eebdba7488acbf9935cc5e050fca235a4e3539fb519d6054b89cdf82f312
3
+ size 9367654912
model-00011-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9627bec72eb925fcefddf075c5749d886e579125473ce75917d7a0c183a81bcb
3
+ size 9966915592
model-00012-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3758b347a024e9aa74a6a91542437a830cf0288e640f7f2bec0042ffa1325d8c
3
+ size 9090764696
model-00013-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39da3860b00850475531a455e14262edcc8492f4935ab944ac4167a77230a384
3
+ size 9367654904
model-00014-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd69a18ec91bcb5445b734857e96ca4b5a5ba758d8e0aa761481633d6dd8fbd
3
+ size 9367654912
model-00015-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb65c351442c533f7464305cab36f0b5917280511d711c3276088a7dec8717e
3
+ size 9966915592
model-00016-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de65c1fefce4c91e33624bf0a16cbc9f4ab21ea480e617d55fbc8b2e97a5d2e2
3
+ size 9090764696
model-00017-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f596a9d34f82c4612100ef9c27387050dfdfa85d5de5d7985380c885e99cd30
3
+ size 9367654904
model-00018-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b188f212a36f4aaf3f47b17bbcff7cb2bf341b9eceacf0d63e8739a5daab59e0
3
+ size 9367654912
model-00019-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92d799227c534ab26cb0a54e3e26abd727fc84b4bfcaa2eeeb00ffaafb9b8f7
3
+ size 9966915592
model-00020-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208bdd8ad1ee398bf47abce96eca159528f92c184eaaf175c502b5b57a18f92c
3
+ size 9090764696
model-00021-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1271c234df92603c79b289d48827633710440f17aa70defddccbd3401b24a345
3
+ size 9367654904
model-00022-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab741f58f3be9e9213912f687cf839a6aa4e5531a9d45dbf7666ce9642d8c673
3
+ size 9367654912
model-00023-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1678525598a93648bf47adc6298364c7b777259898a40db9738f7c9887cd7ea3
3
+ size 9966915592
model-00024-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ffdc6fe4e3cb6c8286082a63902753604ea37d7fcb84dc64a836b430e3968a
3
+ size 9090764696
model-00025-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68329de4a50d442d5902eab0ab2c467be2b6cb7dcaaf29d1b0a0aaaef5541a7
3
+ size 9367654904
model-00026-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69b0105e63bb4d071231784883850539a3e38356c02d42435c5f6c5a636bb1b
3
+ size 9367654912
model-00027-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68940e54b0b0a7b53886cc39e4d23bef46728e298de395b3c720b236e2948d1c
3
+ size 9966915592
model-00028-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b242fed2ac3fca7c54485274e658595d4c026588a67a093ca8212a30cba712c
3
+ size 9090764696
model-00029-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66e2f8ec6d58406d2ad3f9cfef0f6c4d05ec5a3bc8b8cc56db87af567056702
3
+ size 9367654904
model-00030-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393378be8e0c31fec570fae4c5bb8f3b06b3864fdf745826f1fc22188e946177
3
+ size 2927723176
model.safetensors.index.json ADDED
@@ -0,0 +1,1050 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276955168768
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00030-of-00030.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
15
+ "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
16
+ "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
18
+ "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
19
+ "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00030.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
28
+ "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
29
+ "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
31
+ "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
32
+ "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
34
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
35
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
36
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
37
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
38
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
41
+ "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
42
+ "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
43
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
44
+ "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
45
+ "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
47
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
48
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
49
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
50
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
51
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
53
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
54
+ "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
55
+ "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
56
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
57
+ "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
58
+ "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
60
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00030.safetensors",
61
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
62
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
63
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
64
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
65
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
66
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
67
+ "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
68
+ "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
69
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
70
+ "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
71
+ "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
73
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
74
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
75
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
76
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
77
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
78
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
79
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
80
+ "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
81
+ "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
82
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
83
+ "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
84
+ "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
86
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
87
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
88
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
89
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
90
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
91
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
92
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
93
+ "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
94
+ "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
95
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
96
+ "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
97
+ "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
99
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00030.safetensors",
100
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
101
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
102
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
103
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
104
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
105
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
106
+ "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
107
+ "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
108
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
109
+ "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
110
+ "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
112
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
113
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
114
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
115
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
116
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
117
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
118
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
119
+ "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
120
+ "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
121
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
122
+ "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
123
+ "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
125
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
126
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
127
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
128
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
129
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
130
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
131
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
132
+ "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
133
+ "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
134
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
135
+ "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
136
+ "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
138
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00030.safetensors",
139
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
140
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
141
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
142
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
143
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
144
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
145
+ "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
146
+ "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
147
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
148
+ "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
149
+ "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
151
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
152
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
153
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
154
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
155
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
156
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
157
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
158
+ "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
159
+ "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
160
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
161
+ "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
162
+ "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
164
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
165
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
166
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
167
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
168
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
169
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
170
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
171
+ "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
172
+ "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
173
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
174
+ "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
175
+ "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
177
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
178
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
179
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
180
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
181
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
182
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
183
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
184
+ "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
185
+ "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
186
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
187
+ "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
188
+ "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
190
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
191
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
192
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
193
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
194
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
195
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
196
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
197
+ "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
198
+ "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
199
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
200
+ "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
201
+ "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
203
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
204
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
205
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
206
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
207
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
208
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
209
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
210
+ "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
211
+ "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
212
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
213
+ "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
214
+ "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
216
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
217
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
218
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
219
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
220
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
221
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
222
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
223
+ "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
224
+ "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
225
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
226
+ "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
227
+ "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
229
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
230
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
231
+ "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
232
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
233
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
234
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
235
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
236
+ "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
237
+ "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
238
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
239
+ "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
240
+ "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
242
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
243
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
244
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
245
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
246
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
247
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
248
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
249
+ "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
250
+ "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
251
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
252
+ "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
253
+ "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
255
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00030.safetensors",
256
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
257
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
258
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
259
+ "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
260
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
261
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
262
+ "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
263
+ "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
264
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
265
+ "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
266
+ "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
268
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
269
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
270
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
271
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
272
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
273
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
274
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
275
+ "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
276
+ "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
277
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
278
+ "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
279
+ "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
281
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
282
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
283
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
284
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
285
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
286
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
287
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
288
+ "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
289
+ "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
290
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
291
+ "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
292
+ "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
294
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00030.safetensors",
295
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
296
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
297
+ "model.layers.29.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
298
+ "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
299
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
300
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
301
+ "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
302
+ "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
303
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
304
+ "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
305
+ "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
307
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
308
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
309
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
310
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
311
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
312
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
313
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
314
+ "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
315
+ "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
316
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
317
+ "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
318
+ "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
320
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
321
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
322
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
323
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
324
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
325
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
326
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
327
+ "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
328
+ "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
329
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
330
+ "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
331
+ "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
332
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
333
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
334
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
335
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
336
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
337
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
338
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
339
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
340
+ "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
341
+ "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
342
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
343
+ "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
344
+ "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
345
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
346
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
347
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
348
+ "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
349
+ "model.layers.32.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
350
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
351
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
352
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
353
+ "model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
354
+ "model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
355
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
356
+ "model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
357
+ "model.layers.32.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
358
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
359
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
360
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
361
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
362
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
363
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
364
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
365
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
366
+ "model.layers.33.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
367
+ "model.layers.33.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
368
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
369
+ "model.layers.33.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
370
+ "model.layers.33.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
371
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
372
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
373
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
374
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
375
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
376
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
377
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
378
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
379
+ "model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
380
+ "model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
381
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
382
+ "model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
383
+ "model.layers.34.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
384
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
385
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
386
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
387
+ "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
388
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
389
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
390
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
391
+ "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
392
+ "model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
393
+ "model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
394
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
395
+ "model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
396
+ "model.layers.35.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
397
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
398
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
399
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
400
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
401
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
402
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
403
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
404
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
405
+ "model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
406
+ "model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
407
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
408
+ "model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
409
+ "model.layers.36.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
410
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
411
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
412
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
413
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
414
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
415
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
416
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
417
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
418
+ "model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
419
+ "model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
420
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
421
+ "model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
422
+ "model.layers.37.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
423
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
424
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
425
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
426
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
427
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
428
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
429
+ "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
430
+ "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
431
+ "model.layers.38.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
432
+ "model.layers.38.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
433
+ "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
434
+ "model.layers.38.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
435
+ "model.layers.38.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
436
+ "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
437
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
438
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
439
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
440
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
441
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
442
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
443
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
444
+ "model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
445
+ "model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
446
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
447
+ "model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
448
+ "model.layers.39.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
449
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
450
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00030.safetensors",
451
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
452
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
453
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
454
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
455
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
456
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
457
+ "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
458
+ "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
459
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
460
+ "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
461
+ "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
462
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
463
+ "model.layers.40.input_layernorm.weight": "model-00015-of-00030.safetensors",
464
+ "model.layers.40.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
465
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
466
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
467
+ "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
468
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
469
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
470
+ "model.layers.40.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
471
+ "model.layers.40.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
472
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
473
+ "model.layers.40.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
474
+ "model.layers.40.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
475
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
476
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
477
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
478
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
479
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
480
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
481
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
482
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
483
+ "model.layers.41.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
484
+ "model.layers.41.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
485
+ "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
486
+ "model.layers.41.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
487
+ "model.layers.41.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
488
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
489
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
490
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
491
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
492
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
493
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
494
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
495
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
496
+ "model.layers.42.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
497
+ "model.layers.42.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
498
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
499
+ "model.layers.42.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
500
+ "model.layers.42.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
501
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
502
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
503
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
504
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
505
+ "model.layers.43.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
506
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
507
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
508
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
509
+ "model.layers.43.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
510
+ "model.layers.43.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
511
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
512
+ "model.layers.43.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
513
+ "model.layers.43.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
514
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
515
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
516
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
517
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
518
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
519
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
520
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
521
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
522
+ "model.layers.44.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
523
+ "model.layers.44.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
524
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
525
+ "model.layers.44.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
526
+ "model.layers.44.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
527
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
528
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
529
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
530
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
531
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
532
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
533
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
534
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
535
+ "model.layers.45.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
536
+ "model.layers.45.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
537
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
538
+ "model.layers.45.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
539
+ "model.layers.45.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
540
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
541
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
542
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
543
+ "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
544
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
545
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
546
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
547
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
548
+ "model.layers.46.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
549
+ "model.layers.46.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
550
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
551
+ "model.layers.46.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
552
+ "model.layers.46.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
553
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
554
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
555
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
556
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
557
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
558
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
559
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
560
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
561
+ "model.layers.47.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
562
+ "model.layers.47.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
563
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
564
+ "model.layers.47.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
565
+ "model.layers.47.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
566
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
567
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
568
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
569
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
570
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
571
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
572
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
573
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
574
+ "model.layers.48.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
575
+ "model.layers.48.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
576
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
577
+ "model.layers.48.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
578
+ "model.layers.48.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
579
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
580
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
581
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
582
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
583
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
584
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
585
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
586
+ "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
587
+ "model.layers.49.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
588
+ "model.layers.49.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
589
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
590
+ "model.layers.49.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
591
+ "model.layers.49.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
592
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
593
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
594
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
595
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
596
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
597
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
598
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
599
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
600
+ "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
601
+ "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
602
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
603
+ "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
604
+ "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
605
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
606
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
607
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
608
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
609
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
610
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
611
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
612
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
613
+ "model.layers.50.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
614
+ "model.layers.50.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
615
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
616
+ "model.layers.50.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
617
+ "model.layers.50.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
618
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
619
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
620
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
621
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
622
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
623
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
624
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
625
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
626
+ "model.layers.51.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
627
+ "model.layers.51.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
628
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
629
+ "model.layers.51.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
630
+ "model.layers.51.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
631
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
632
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
633
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
634
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
635
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
636
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
637
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
638
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
639
+ "model.layers.52.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
640
+ "model.layers.52.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
641
+ "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
642
+ "model.layers.52.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
643
+ "model.layers.52.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
644
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
645
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
646
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
647
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
648
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
649
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
650
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
651
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
652
+ "model.layers.53.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
653
+ "model.layers.53.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
654
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
655
+ "model.layers.53.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
656
+ "model.layers.53.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
657
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
658
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
659
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
660
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
661
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
662
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
663
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
664
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
665
+ "model.layers.54.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
666
+ "model.layers.54.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
667
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
668
+ "model.layers.54.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
669
+ "model.layers.54.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
670
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
671
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
672
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
673
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
674
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
675
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
676
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
677
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
678
+ "model.layers.55.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
679
+ "model.layers.55.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
680
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
681
+ "model.layers.55.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
682
+ "model.layers.55.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
683
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
684
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
685
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
686
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
687
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
688
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
689
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
690
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
691
+ "model.layers.56.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
692
+ "model.layers.56.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
693
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
694
+ "model.layers.56.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
695
+ "model.layers.56.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
696
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
697
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
698
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
699
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
700
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
701
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
702
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
703
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
704
+ "model.layers.57.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
705
+ "model.layers.57.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
706
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
707
+ "model.layers.57.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
708
+ "model.layers.57.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
709
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
710
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
711
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
712
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
713
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
714
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
715
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
716
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
717
+ "model.layers.58.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
718
+ "model.layers.58.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
719
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
720
+ "model.layers.58.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
721
+ "model.layers.58.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
722
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
723
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
724
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
725
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
726
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
727
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
728
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
729
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
730
+ "model.layers.59.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
731
+ "model.layers.59.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
732
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
733
+ "model.layers.59.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
734
+ "model.layers.59.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
735
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
736
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
737
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
738
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
739
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
740
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
741
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
742
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
743
+ "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
744
+ "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
745
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
746
+ "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
747
+ "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
748
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
749
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
750
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
751
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
752
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
753
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
754
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
755
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
756
+ "model.layers.60.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
757
+ "model.layers.60.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
758
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
759
+ "model.layers.60.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
760
+ "model.layers.60.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
761
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
762
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
763
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
764
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
765
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
766
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
767
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
768
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
769
+ "model.layers.61.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
770
+ "model.layers.61.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
771
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
772
+ "model.layers.61.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
773
+ "model.layers.61.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
774
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
775
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
776
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
777
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
778
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
779
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
780
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
781
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
782
+ "model.layers.62.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
783
+ "model.layers.62.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
784
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
785
+ "model.layers.62.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
786
+ "model.layers.62.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
787
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
788
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
789
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
790
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
791
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
792
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
793
+ "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
794
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
795
+ "model.layers.63.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
796
+ "model.layers.63.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
797
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
798
+ "model.layers.63.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
799
+ "model.layers.63.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
800
+ "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
801
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
802
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
803
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
804
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
805
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
806
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
807
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
808
+ "model.layers.64.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
809
+ "model.layers.64.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
810
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
811
+ "model.layers.64.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
812
+ "model.layers.64.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
813
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
814
+ "model.layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
815
+ "model.layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
816
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
817
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
818
+ "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
819
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
820
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
821
+ "model.layers.65.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
822
+ "model.layers.65.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
823
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
824
+ "model.layers.65.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
825
+ "model.layers.65.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
826
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
827
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
828
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
829
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
830
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
831
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
832
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
833
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
834
+ "model.layers.66.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
835
+ "model.layers.66.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
836
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
837
+ "model.layers.66.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
838
+ "model.layers.66.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
839
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
840
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
841
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
842
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
843
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
844
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
845
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
846
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
847
+ "model.layers.67.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
848
+ "model.layers.67.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
849
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
850
+ "model.layers.67.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
851
+ "model.layers.67.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
852
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
853
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
854
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
855
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
856
+ "model.layers.68.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
857
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
858
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
859
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
860
+ "model.layers.68.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
861
+ "model.layers.68.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
862
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
863
+ "model.layers.68.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
864
+ "model.layers.68.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
865
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
866
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
867
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
868
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
869
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
870
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
871
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
872
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
873
+ "model.layers.69.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
874
+ "model.layers.69.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
875
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
876
+ "model.layers.69.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
877
+ "model.layers.69.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
878
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
879
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00030.safetensors",
880
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
881
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
882
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
883
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
884
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
885
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
886
+ "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
887
+ "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
888
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
889
+ "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
890
+ "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
891
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
892
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
893
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
894
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
895
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
896
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
897
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
898
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
899
+ "model.layers.70.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
900
+ "model.layers.70.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
901
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
902
+ "model.layers.70.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
903
+ "model.layers.70.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
904
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
905
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
906
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
907
+ "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
908
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
909
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
910
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
911
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
912
+ "model.layers.71.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
913
+ "model.layers.71.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
914
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
915
+ "model.layers.71.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
916
+ "model.layers.71.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
917
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
918
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
919
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
920
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
921
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
922
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
923
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
924
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
925
+ "model.layers.72.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
926
+ "model.layers.72.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
927
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
928
+ "model.layers.72.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
929
+ "model.layers.72.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
930
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
931
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
932
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
933
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
934
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
935
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
936
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
937
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
938
+ "model.layers.73.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
939
+ "model.layers.73.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
940
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
941
+ "model.layers.73.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
942
+ "model.layers.73.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
943
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
944
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
945
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
946
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
947
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
948
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
949
+ "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
950
+ "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
951
+ "model.layers.74.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
952
+ "model.layers.74.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
953
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
954
+ "model.layers.74.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
955
+ "model.layers.74.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
956
+ "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
957
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
958
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
959
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
960
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
961
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
962
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
963
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
964
+ "model.layers.75.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
965
+ "model.layers.75.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
966
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
967
+ "model.layers.75.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
968
+ "model.layers.75.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
969
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
970
+ "model.layers.76.input_layernorm.weight": "model-00029-of-00030.safetensors",
971
+ "model.layers.76.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
972
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
973
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
974
+ "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
975
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
976
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
977
+ "model.layers.76.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
978
+ "model.layers.76.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
979
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
980
+ "model.layers.76.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
981
+ "model.layers.76.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
982
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
983
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
984
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
985
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
986
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
987
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
988
+ "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
989
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
990
+ "model.layers.77.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
991
+ "model.layers.77.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
992
+ "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
993
+ "model.layers.77.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
994
+ "model.layers.77.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
995
+ "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
996
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
997
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
998
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
999
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
1000
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
1001
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1002
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1003
+ "model.layers.78.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1004
+ "model.layers.78.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1005
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1006
+ "model.layers.78.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1007
+ "model.layers.78.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1008
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1009
+ "model.layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
1010
+ "model.layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
1011
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
1012
+ "model.layers.79.mlp.up_proj.weight": "model-00030-of-00030.safetensors",
1013
+ "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
1014
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1015
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1016
+ "model.layers.79.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1017
+ "model.layers.79.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1018
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1019
+ "model.layers.79.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1020
+ "model.layers.79.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1021
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1022
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
1023
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
1024
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1025
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1026
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
1027
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1028
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1029
+ "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
1030
+ "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
1031
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
1032
+ "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1033
+ "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1034
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1035
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
1036
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
1037
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1038
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1039
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
1040
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1041
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1042
+ "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1043
+ "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1044
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
1045
+ "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1046
+ "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1047
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1048
+ "model.norm.weight": "model-00030-of-00030.safetensors"
1049
+ }
1050
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "max_length": 2048,
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "stride": 0,
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "truncation_side": "right",
28
+ "truncation_strategy": "longest_first",
29
+ "unk_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "use_default_system_prompt": true
38
+ }