bengali model
Browse files- config.json +24 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00034.bin +3 -0
- pytorch_model-00002-of-00034.bin +3 -0
- pytorch_model-00003-of-00034.bin +3 -0
- pytorch_model-00004-of-00034.bin +3 -0
- pytorch_model-00005-of-00034.bin +3 -0
- pytorch_model-00006-of-00034.bin +3 -0
- pytorch_model-00007-of-00034.bin +3 -0
- pytorch_model-00008-of-00034.bin +3 -0
- pytorch_model-00009-of-00034.bin +3 -0
- pytorch_model-00010-of-00034.bin +3 -0
- pytorch_model-00011-of-00034.bin +3 -0
- pytorch_model-00012-of-00034.bin +3 -0
- pytorch_model-00013-of-00034.bin +3 -0
- pytorch_model-00014-of-00034.bin +3 -0
- pytorch_model-00015-of-00034.bin +3 -0
- pytorch_model-00016-of-00034.bin +3 -0
- pytorch_model-00017-of-00034.bin +3 -0
- pytorch_model-00018-of-00034.bin +3 -0
- pytorch_model-00019-of-00034.bin +3 -0
- pytorch_model-00020-of-00034.bin +3 -0
- pytorch_model-00021-of-00034.bin +3 -0
- pytorch_model-00022-of-00034.bin +3 -0
- pytorch_model-00023-of-00034.bin +3 -0
- pytorch_model-00024-of-00034.bin +3 -0
- pytorch_model-00025-of-00034.bin +3 -0
- pytorch_model-00026-of-00034.bin +3 -0
- pytorch_model-00027-of-00034.bin +3 -0
- pytorch_model-00028-of-00034.bin +3 -0
- pytorch_model-00029-of-00034.bin +3 -0
- pytorch_model-00030-of-00034.bin +3 -0
- pytorch_model-00031-of-00034.bin +3 -0
- pytorch_model-00032-of-00034.bin +3 -0
- pytorch_model-00033-of-00034.bin +3 -0
- pytorch_model-00034-of-00034.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +23 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "decapoda-research/llama-7b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 1,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"pad_token_id": -1,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.31.0.dev0",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000
|
24 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.31.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09460eb3226dd4f1a165ccd6d93f8a340b10a08ea71d9fd03f0b274ebf34d41e
|
3 |
+
size 396364479
|
pytorch_model-00002-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b449f4e0b179696fbcbe33650708b605683eb7ef3129078841e0226046240f8a
|
3 |
+
size 404770755
|
pytorch_model-00003-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75dc7b3c2a5817690972544137e6e204326205b764f098477f4ccf12bab6e39e
|
3 |
+
size 404770755
|
pytorch_model-00004-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b1b3e0e484eaf0bdd9f499b253dca90a7e80cff6e58276c6de84f739e88ab9d
|
3 |
+
size 404770755
|
pytorch_model-00005-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49bfb6b0255676203620effb5e5484ef4db04f38824d738faa987220dfd78af
|
3 |
+
size 404770755
|
pytorch_model-00006-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f1462237dd46b1173da7706e6b03494eaf89e26118eb3634c8b9c4d61cb0df3
|
3 |
+
size 404770755
|
pytorch_model-00007-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecd2202ba691ec12910b9aab8ea451aa8bacb89db2a88966453a845a2c88d7ad
|
3 |
+
size 404770755
|
pytorch_model-00008-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84db43a0b1f8835c8f82571efb94e426baf18de9b9ada75a7fb964c3443726b6
|
3 |
+
size 404770755
|
pytorch_model-00009-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8714b8abbec3ea506b89f0decebefec3fd2ab5087374fd636483e3274f6d205b
|
3 |
+
size 404770755
|
pytorch_model-00010-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bdfc7a074b26418647d23379ff589b7b5fc65bb946a255fad992dfaa269eaf1
|
3 |
+
size 404770755
|
pytorch_model-00011-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60e3691a6f725be7186ff308b7094a8e375f01e23292ebb55a2ae51008d9276
|
3 |
+
size 404770755
|
pytorch_model-00012-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61751cc74995456b37e4e800f505a2cf0802cf7bb54a2237722063c6a4842ce2
|
3 |
+
size 404770755
|
pytorch_model-00013-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:859ff0ee0640100afde6bc98a1cf1b22a84235e48a95b93fc4d40c5aaf64ccfd
|
3 |
+
size 404770755
|
pytorch_model-00014-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96ada1dc830bc203842ed247c34b678006a314ff2b50eec4ea122d1455d4af9c
|
3 |
+
size 404770755
|
pytorch_model-00015-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dc892deda7955a7c4080bd0df2294032fdd3cc12b60c46b147ae3bcee130ca7
|
3 |
+
size 404770755
|
pytorch_model-00016-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d889f7d4b58cb7702d74690194567db69c5770356ca7d659a13ca19804a971a
|
3 |
+
size 404770755
|
pytorch_model-00017-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdbba30b1d88cb42f45bfeb6c24c61d3f685a6faa78d00a119cc9dfc8b88a320
|
3 |
+
size 404770755
|
pytorch_model-00018-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5daa1f443db3352f8d374c5a5366974d6ab98f723a52cf981ffb5830f039fd37
|
3 |
+
size 404770755
|
pytorch_model-00019-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080e2095aec86821804a87d55765b9e358ca9c27b094a4bd80123a43a9aad589
|
3 |
+
size 404770755
|
pytorch_model-00020-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1df7490c5b14f861f24ab90cdaea0358aaad1b04890d0e94c41552c11681151b
|
3 |
+
size 404770755
|
pytorch_model-00021-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08bc1d93f3f1e1a30c882dc1d30911e58637afc40648c05aa516a03cee4ace92
|
3 |
+
size 404770755
|
pytorch_model-00022-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ea3ab4d33686b43582f7ad3ca0bce099f5106625444c78304471867a2083197
|
3 |
+
size 404770755
|
pytorch_model-00023-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7686d217eabf21c2eb2b36ac1062c00cbb068fbfec8cf7cdd4ac589a9c419519
|
3 |
+
size 404770755
|
pytorch_model-00024-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b07419efd698ace2a4a6842aa1a73f16ab6230f8eff8c1e3eff9fb5100b5e5ab
|
3 |
+
size 404770755
|
pytorch_model-00025-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99f3bb47461529030af0fa318ac4b79e9d2cc40fa72de2cb753b54660db2e668
|
3 |
+
size 404770755
|
pytorch_model-00026-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:791648383b95d461dacd9cebbc0cd9b6ffcb135c9aa3157fee846bb61c076f0e
|
3 |
+
size 404770755
|
pytorch_model-00027-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf6444a7f32ffd1c9ac3b4e24b0bca7c3a978b463c13d10babfab272cdc1490d
|
3 |
+
size 404770755
|
pytorch_model-00028-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efdec9481f5264624c5469bddfccf3a5d4cb3df7d3449a07f709a72d6b8d5c45
|
3 |
+
size 404770755
|
pytorch_model-00029-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3aa1441d64871228111d49067eaeb14131e9a925f709d2edfab413ca5945ff9
|
3 |
+
size 404770755
|
pytorch_model-00030-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70f521b38256b67fedc984c873d275e0953b96dc9254fa7365c43be4902f72fd
|
3 |
+
size 404770755
|
pytorch_model-00031-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e70c7f8f8b4f07c6142cdfb2630b5c33930c21da04cca12daddbea6d47426ea
|
3 |
+
size 404770755
|
pytorch_model-00032-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d96027f1782a3242d23341fc0a7c39e8c0acb40dbe76fcf80c3f2b871753f432
|
3 |
+
size 404770755
|
pytorch_model-00033-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dee36ae45bd7beb69a1541f95b5a09ab6010cb605134c813171ff588a3551ad
|
3 |
+
size 270559679
|
pytorch_model-00034-of-00034.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee7ac3b7a8c1da89a74a5552c54410ff966dbc7c8de1edaa100732ad0e811336
|
3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476839424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00034-of-00034.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00033-of-00034.bin"
|
329 |
+
}
|
330 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"use_fast": false
|
34 |
+
}
|