Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +37 -0
- mergekit_moe_config.yml +8 -0
- model-00001-of-00059.safetensors +3 -0
- model-00002-of-00059.safetensors +3 -0
- model-00003-of-00059.safetensors +3 -0
- model-00004-of-00059.safetensors +3 -0
- model-00005-of-00059.safetensors +3 -0
- model-00006-of-00059.safetensors +3 -0
- model-00007-of-00059.safetensors +3 -0
- model-00008-of-00059.safetensors +3 -0
- model-00009-of-00059.safetensors +3 -0
- model-00010-of-00059.safetensors +3 -0
- model-00011-of-00059.safetensors +3 -0
- model-00012-of-00059.safetensors +3 -0
- model-00013-of-00059.safetensors +3 -0
- model-00014-of-00059.safetensors +3 -0
- model-00015-of-00059.safetensors +3 -0
- model-00016-of-00059.safetensors +3 -0
- model-00017-of-00059.safetensors +3 -0
- model-00018-of-00059.safetensors +3 -0
- model-00019-of-00059.safetensors +3 -0
- model-00020-of-00059.safetensors +3 -0
- model-00021-of-00059.safetensors +3 -0
- model-00022-of-00059.safetensors +3 -0
- model-00023-of-00059.safetensors +3 -0
- model-00024-of-00059.safetensors +3 -0
- model-00025-of-00059.safetensors +3 -0
- model-00026-of-00059.safetensors +3 -0
- model-00027-of-00059.safetensors +3 -0
- model-00028-of-00059.safetensors +3 -0
- model-00029-of-00059.safetensors +3 -0
- model-00030-of-00059.safetensors +3 -0
- model-00031-of-00059.safetensors +3 -0
- model-00032-of-00059.safetensors +3 -0
- model-00033-of-00059.safetensors +3 -0
- model-00034-of-00059.safetensors +3 -0
- model-00035-of-00059.safetensors +3 -0
- model-00036-of-00059.safetensors +3 -0
- model-00037-of-00059.safetensors +3 -0
- model-00038-of-00059.safetensors +3 -0
- model-00039-of-00059.safetensors +3 -0
- model-00040-of-00059.safetensors +3 -0
- model-00041-of-00059.safetensors +3 -0
- model-00042-of-00059.safetensors +3 -0
- model-00043-of-00059.safetensors +3 -0
- model-00044-of-00059.safetensors +3 -0
- model-00045-of-00059.safetensors +3 -0
- model-00046-of-00059.safetensors +3 -0
- model-00047-of-00059.safetensors +3 -0
- model-00048-of-00059.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Sakalti/SJT-7.5B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 11,
|
9 |
+
"eos_token_id": 11,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 23040,
|
15 |
+
"max_position_embeddings": 32768,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "mixtral",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_experts_per_tok": 2,
|
20 |
+
"num_hidden_layers": 28,
|
21 |
+
"num_key_value_heads": 4,
|
22 |
+
"num_local_experts": 2,
|
23 |
+
"output_router_logits": false,
|
24 |
+
"pad_token_id": 2023,
|
25 |
+
"pretraining_tp": 1,
|
26 |
+
"rms_norm_eps": 1e-06,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 1000042,
|
29 |
+
"router_aux_loss_coef": 0.001,
|
30 |
+
"router_jitter_noise": 0.0,
|
31 |
+
"sliding_window": null,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "float16",
|
34 |
+
"transformers_version": "4.46.3",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 131072
|
37 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: Sakalti/SJT-7.5B
|
2 |
+
gate_mode: random
|
3 |
+
dtype: float16
|
4 |
+
experts:
|
5 |
+
- source_model: Sakalti/SJT-7.5B
|
6 |
+
positive_prompts: [hello, こんにちは, おはようございます。,お元気ですか?]
|
7 |
+
- source_model: Sakalti/SJT-7.5B
|
8 |
+
negative_prompts: [bad]
|
model-00001-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64361f97fdddceb0c78323c43e067299a9bc2142fe8f705141b27ed7711d430d
|
3 |
+
size 805306504
|
model-00002-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b35801653e374d658d5bbce8b6c7d9796f0912b138bec8c29656af17d8c33ac
|
3 |
+
size 475018320
|
model-00003-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e93a1bb46ad2e2b9867b49d21ccee1fda8a9ee7f8302c437ceb2f25300b904a9
|
3 |
+
size 475018320
|
model-00004-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c407bb98cdb2d3e8e0fdd04c0ac9a995ca1e521c413ada70c582e6f58b11a34a
|
3 |
+
size 424673696
|
model-00005-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03d196df0f328772bf87532d4249265b0af1270206e9933aa32bede2551ab2cb
|
3 |
+
size 475018320
|
model-00006-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb6d4a33696e1af408ae7990fe6ff084fc419b04e66ed426d3353134b52b692
|
3 |
+
size 424673696
|
model-00007-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:865eb9a171a26f724f46a8e38ecf4ecf256f2d3fef5b92db06bb354f32f215fd
|
3 |
+
size 475018320
|
model-00008-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c0e3c9727c778d3e400322947e2e5a44b1eeb781e620a460eaebbff2047f9d
|
3 |
+
size 424673696
|
model-00009-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c2ee41d52d271527067635e8e9d4b2fb4878119f80d058ccbc5bf35f1f44747
|
3 |
+
size 475018320
|
model-00010-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36f32607b6a33b969389021c24d0bad012d65b81a89bcbee6051be1d863e57bd
|
3 |
+
size 424673696
|
model-00011-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:770437b70191cc18fd88a287ad21301c769751be7645a7ce6ff26da68771f972
|
3 |
+
size 475018320
|
model-00012-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cb9e9848c61efbb55b5e448b04861bc5cfaf62efec621988e5227c559e366b4
|
3 |
+
size 424673696
|
model-00013-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13fd36302781b134e544f25c301dd820537f0fcd16778dec99cdaa82dcf5c558
|
3 |
+
size 475018320
|
model-00014-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c918c0359c83c3f52e01f7d4ecf95cee880597be7642db7f686af6d9f96662c8
|
3 |
+
size 424673696
|
model-00015-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704efca01c30d753ab4efc3cac9b8437047cc674b743d6496ddda0f24e5750f1
|
3 |
+
size 475018320
|
model-00016-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1404dcd781837dc05d961e0f0ee9c5239650f850b865ae3c723e075831507514
|
3 |
+
size 424673696
|
model-00017-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7672002fd91851c403170ae73015996b8e6f5fb532623c490e8f2182f05c58d7
|
3 |
+
size 475018320
|
model-00018-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d371d363267076edd817f92066bf7c560350b60d80b83a3bc34e120b6098954f
|
3 |
+
size 424673696
|
model-00019-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9454821f32aee2e13fd5ca75f1024943a14b61e410704fe413424393438b2312
|
3 |
+
size 475018320
|
model-00020-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120439e4e05107aaed6bd14d20ad7b380aef8663c56ce61a6b4fa7731512080e
|
3 |
+
size 424673696
|
model-00021-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dc05b916134f7b8ca553c50eb0a9a29eaa7add53add41ed692d854580f12c29
|
3 |
+
size 475018296
|
model-00022-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddbd9501a77431ae1c9a764d55789b352e5dc2f9f260d83da44dc0905c17fa3d
|
3 |
+
size 424673704
|
model-00023-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8001b75823d9594c889a16af66cd04159318493e9eb40f5b9e3ed103c184456
|
3 |
+
size 475018328
|
model-00024-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e618b5207a23e97f2dcbff9733a6add8153a9b21cf8a52e13bc96e5c4acfc8d5
|
3 |
+
size 424673704
|
model-00025-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3f9c2bfa1750d434343b92b4c9c8b4d25a1f16287d9e90c1965b46f3fa77b1e
|
3 |
+
size 475018328
|
model-00026-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd940bfc755eccc82ec809a0fd4388ad0301c0f89afb01c3fd1acdbf5a6a132
|
3 |
+
size 424673704
|
model-00027-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd185da1df913f556de3a4c42022186a48c71dc1814b171d48a14d1b77c0acba
|
3 |
+
size 475018328
|
model-00028-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9e5ff6a0a17913b25b609a5bcd076e037559863deb15b8dfe980a5e72a10862
|
3 |
+
size 424673704
|
model-00029-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f12c92b41d7a51003696ca65798644df1157965ab1b2fee0d4cfc462ae03441c
|
3 |
+
size 475018328
|
model-00030-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abf74ad8efaa982be5fda7adb73148db2d8beab4b982e9da9ccb9192d1880a00
|
3 |
+
size 424673704
|
model-00031-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8d41a1c89076bad44c8266b0b25db5846b33870e85d39337332b6623fdb6c8e
|
3 |
+
size 475018328
|
model-00032-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac4ad93b797464e2b1df2a5a83df3fef1ec7b0c7a1af7802e7e80ca84a300ee3
|
3 |
+
size 424673704
|
model-00033-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01086b2d2f090e9bbbdf4f854fcfd1b2520af42b33c8378b02d5ed8346db526b
|
3 |
+
size 475018328
|
model-00034-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e371907b1cd5f320779477d722e5cce42ab8656cf03407639d4f859bd13e81e2
|
3 |
+
size 424673704
|
model-00035-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:691aabfccfb94c0b3f72589bda6f5ec816df17e0d67e949f0e990603d2eee5c0
|
3 |
+
size 475018328
|
model-00036-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b33dad7bb8ac731daffa0138fce89d76cabaa204e6679824c5f7bbfae11d2ab
|
3 |
+
size 424673704
|
model-00037-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b6216d7ff527fa45a52e154898445f8cdf4a8b64f3b645dacbed28df9126fa2
|
3 |
+
size 475018328
|
model-00038-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec01a7b1c75ceb87803908912de58f44584d01c8b10b344dd4bdde26551ce9d4
|
3 |
+
size 424673704
|
model-00039-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8f7fe5b3d16e9f798ec6d05147db4edb5117c14e5226cb1c594fab2f2bf8de
|
3 |
+
size 475018328
|
model-00040-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b4e9e65078da9aa3083d211ad23dcf22a55fd8d2cddd679737f19fde1b031f5
|
3 |
+
size 424673704
|
model-00041-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6ad887d389559bf0e031b479d95e43b4422ddf6c8dde0b90f92d402c4a6d58
|
3 |
+
size 475018328
|
model-00042-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04590ce0a158cec894a3d9363996b4ee3a110dc99bbd910033314fa48133cbdd
|
3 |
+
size 424673704
|
model-00043-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9928f18c696490f13f1d6ad9f94219b8ccfc048a91535e22b65fad85dd484f3
|
3 |
+
size 475018328
|
model-00044-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de5771cec4bb3114b199e6b88e08996f042610efba0640c953d5fa41aec90954
|
3 |
+
size 424673704
|
model-00045-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c6c39ff689761cb8082052284709ccafef2437d5534d1106a1d7903d8561f81
|
3 |
+
size 475018328
|
model-00046-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06b196a749d885994ddcd46aa8c03dfc299f46145140157634e7a308f15ae03c
|
3 |
+
size 424673704
|
model-00047-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f192b10525fbd2f9144a984bdf6f21af3a444664f7609312b7d06ac3bf5eb302
|
3 |
+
size 475018328
|
model-00048-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a749082482976f3289d848b7e09ebfafe71e1be66a7834fe6b53a83c2d1fe1f3
|
3 |
+
size 424673704
|