Upload folder using huggingface_hub
Browse files- config.json +32 -0
- model-00001-of-00021.safetensors +3 -0
- model-00002-of-00021.safetensors +3 -0
- model-00003-of-00021.safetensors +3 -0
- model-00004-of-00021.safetensors +3 -0
- model-00005-of-00021.safetensors +3 -0
- model-00006-of-00021.safetensors +3 -0
- model-00007-of-00021.safetensors +3 -0
- model-00008-of-00021.safetensors +3 -0
- model-00009-of-00021.safetensors +3 -0
- model-00010-of-00021.safetensors +3 -0
- model-00011-of-00021.safetensors +3 -0
- model-00012-of-00021.safetensors +3 -0
- model-00013-of-00021.safetensors +3 -0
- model-00014-of-00021.safetensors +3 -0
- model-00015-of-00021.safetensors +3 -0
- model-00016-of-00021.safetensors +3 -0
- model-00017-of-00021.safetensors +3 -0
- model-00018-of-00021.safetensors +3 -0
- model-00019-of-00021.safetensors +3 -0
- model-00020-of-00021.safetensors +3 -0
- model-00021-of-00021.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MixtralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mlp_bias": false,
|
| 15 |
+
"model_type": "mixtral",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_experts_per_tok": 2,
|
| 18 |
+
"num_hidden_layers": 16,
|
| 19 |
+
"num_key_value_heads": 16,
|
| 20 |
+
"num_local_experts": 128,
|
| 21 |
+
"output_router_logits": false,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_theta": 10000,
|
| 24 |
+
"router_aux_loss_coef": 0.01,
|
| 25 |
+
"router_jitter_noise": 0.0,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.46.0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 99584
|
| 32 |
+
}
|
model-00001-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71909bf165120d62616fec1a29e2727efdcafb53d70d4658bf6b120a5d0bdbbd
|
| 3 |
+
size 4996640360
|
model-00002-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86649785d78a14ab886f3684449dbf77f1c52a6ec126113ee5c9eddf444bcf7c
|
| 3 |
+
size 4999649184
|
model-00003-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f06e09e86bd7a29e92734c647e1bdf891eb671814d28032bb0b0a81ce8362287
|
| 3 |
+
size 4999649400
|
model-00004-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83a5495012ccc7b3dd7801a226a834ebf3d36c9c60576d9d7b22ddf4bcc5c7dc
|
| 3 |
+
size 4999649312
|
model-00005-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:141ece5ee44bc8707d43a9ff7bd4c205f66c741f63ea020b7fc7a3c58977d598
|
| 3 |
+
size 4999649496
|
model-00006-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2267801f253a4ddb0952bf8c364b6613ed0b55028b7f48ad9217f44225014f0
|
| 3 |
+
size 4999649416
|
model-00007-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c94211ab501143b146b8deaf1f2c548ae5cc824d0146ad7d24f86ad425647cf7
|
| 3 |
+
size 4999649328
|
model-00008-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:733888594add8735ca1410b2a15b6889b5e1116756041d160cfb9af2239f546c
|
| 3 |
+
size 4999649584
|
model-00009-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86d18c3d47f4c8695eabf9fabc40c6b3b87491989adea30ede4c710ef61fcf01
|
| 3 |
+
size 4999649312
|
model-00010-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eabf75c2b5ae5568fb31ab9d7cfec1eb59840f486b89c5388e0f4a56337827e4
|
| 3 |
+
size 4999649448
|
model-00011-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b935a053c86e14be0c9d6a54d0c3dac93fd0d638dea1a29ce1034c9ffb360f9d
|
| 3 |
+
size 4999649464
|
model-00012-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7bdd0adc93bb364eb938c26d5dceb26ba615925aa0bdb8bf03588c53d4729ba
|
| 3 |
+
size 4999649312
|
model-00013-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8aeea44acf86a059bd976d477d4e2d36f357d6e082a8888ef57c03bc778f740
|
| 3 |
+
size 4999649576
|
model-00014-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ac85a6c742fa409f2ac4f8547f6fe4f535f3987e09cc15eb85b2aa800e4cba3
|
| 3 |
+
size 4999649336
|
model-00015-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88604a4999c2e0776aeb1a9563f2d205581a523846b97b52b4bd2aa53f7b92de
|
| 3 |
+
size 4999649408
|
model-00016-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb994331b6451ac171afac01b72076c414c3b5143c1db57d159414515960aec
|
| 3 |
+
size 4999649576
|
model-00017-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0e5e753ad23389781867821a5be71603012b9ac4d12af2673346a682cc8de60
|
| 3 |
+
size 4999649536
|
model-00018-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b839bdbf33dbbeca65e079970d95165927c534fb2572dc2d4b9e956ea9f166c
|
| 3 |
+
size 4999649760
|
model-00019-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:266e1242cf9f6656884c02ff5cac54f05e7801414c9717bce311a5d071323d05
|
| 3 |
+
size 4999649664
|
model-00020-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64c262adee991a1683199e677a53ae896caf8ab24820c576930c7aa8d10d3ed
|
| 3 |
+
size 4999649656
|
model-00021-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b45a11c4265831d5f218efa2ed99c1e9e125d0010e340813c0f8700d392e73a6
|
| 3 |
+
size 4451241416
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<CLS|LLM-jp>",
|
| 4 |
+
"eod_token": "</s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<MASK|LLM-jp>",
|
| 7 |
+
"pad_token": "<PAD|LLM-jp>",
|
| 8 |
+
"sep_token": "<SEP|LLM-jp>",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"pad_token": "<PAD|LLM-jp>",
|
| 8 |
+
"cls_token": "<CLS|LLM-jp>",
|
| 9 |
+
"sep_token": "<SEP|LLM-jp>",
|
| 10 |
+
"eod_token": "</s>",
|
| 11 |
+
"mask_token": "<MASK|LLM-jp>",
|
| 12 |
+
"extra_ids": 0,
|
| 13 |
+
"sp_model_kwargs": {},
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
+
"clean_up_tokenization_spaces": false,
|
| 16 |
+
"special_tokens_map_file": null,
|
| 17 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 18 |
+
}
|