first commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +34 -0
- generation_config.json +6 -0
- model-00001-of-00060.safetensors +3 -0
- model-00002-of-00060.safetensors +3 -0
- model-00003-of-00060.safetensors +3 -0
- model-00004-of-00060.safetensors +3 -0
- model-00005-of-00060.safetensors +3 -0
- model-00006-of-00060.safetensors +3 -0
- model-00007-of-00060.safetensors +3 -0
- model-00008-of-00060.safetensors +3 -0
- model-00009-of-00060.safetensors +3 -0
- model-00010-of-00060.safetensors +3 -0
- model-00011-of-00060.safetensors +3 -0
- model-00012-of-00060.safetensors +3 -0
- model-00013-of-00060.safetensors +3 -0
- model-00014-of-00060.safetensors +3 -0
- model-00015-of-00060.safetensors +3 -0
- model-00016-of-00060.safetensors +3 -0
- model-00017-of-00060.safetensors +3 -0
- model-00018-of-00060.safetensors +3 -0
- model-00019-of-00060.safetensors +3 -0
- model-00020-of-00060.safetensors +3 -0
- model-00021-of-00060.safetensors +3 -0
- model-00022-of-00060.safetensors +3 -0
- model-00023-of-00060.safetensors +3 -0
- model-00024-of-00060.safetensors +3 -0
- model-00025-of-00060.safetensors +3 -0
- model-00026-of-00060.safetensors +3 -0
- model-00027-of-00060.safetensors +3 -0
- model-00028-of-00060.safetensors +3 -0
- model-00029-of-00060.safetensors +3 -0
- model-00030-of-00060.safetensors +3 -0
- model-00031-of-00060.safetensors +3 -0
- model-00032-of-00060.safetensors +3 -0
- model-00033-of-00060.safetensors +3 -0
- model-00034-of-00060.safetensors +3 -0
- model-00035-of-00060.safetensors +3 -0
- model-00036-of-00060.safetensors +3 -0
- model-00037-of-00060.safetensors +3 -0
- model-00038-of-00060.safetensors +3 -0
- model-00039-of-00060.safetensors +3 -0
- model-00040-of-00060.safetensors +3 -0
- model-00041-of-00060.safetensors +3 -0
- model-00042-of-00060.safetensors +3 -0
- model-00043-of-00060.safetensors +3 -0
- model-00044-of-00060.safetensors +3 -0
- model-00045-of-00060.safetensors +3 -0
- model-00046-of-00060.safetensors +3 -0
- model-00047-of-00060.safetensors +3 -0
- model-00048-of-00060.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/sip3-aizawa-test/shared/kkobayashi/002_SIP-pre2-8x13b_CPT_MedCv2OP/checkpoints_hf/iter_0010551",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 13824,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "mixtral",
|
18 |
+
"num_attention_heads": 40,
|
19 |
+
"num_experts_per_tok": 2,
|
20 |
+
"num_hidden_layers": 40,
|
21 |
+
"num_key_value_heads": 40,
|
22 |
+
"num_local_experts": 8,
|
23 |
+
"output_router_logits": false,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_theta": 10000,
|
26 |
+
"router_aux_loss_coef": 0.01,
|
27 |
+
"router_jitter_noise": 0.0,
|
28 |
+
"sliding_window": null,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.47.0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 99584
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.47.0"
|
6 |
+
}
|
model-00001-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1347453dd242e59923baf955205f7aab8af3cb9dc33bce421df68e058b03789
|
3 |
+
size 4724000480
|
model-00002-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04752ef95a6fb2fb98738f1b3327891678f989d120942e2ca9da87407c54452
|
3 |
+
size 4949486440
|
model-00003-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b0e3ed6395b4660b2ce7ea27063bf509c700ddc6b8fa9b9b526ce10bc728d0
|
3 |
+
size 4812966080
|
model-00004-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74c61623f46fca7a94dd617a6ab5119d217b4c24155b7f0943a4d878aaf09216
|
3 |
+
size 4949486440
|
model-00005-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e382f3da325f7c6d128d205bc3c5fe215734b993174a958668919a18f137ff4d
|
3 |
+
size 4949486440
|
model-00006-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4fe3557bf6003d284f1f378a544e399e214162fdbd0825e4380c5cad2b33e4
|
3 |
+
size 4812966080
|
model-00007-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a14c24dd8ff6e7b7629133cb45f0f483018711e7bb336262a4c819ec5156ae7f
|
3 |
+
size 4949486440
|
model-00008-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31cc1c5ad7ca1c3046b7b3cb11e6bec1bf5d89d38e92623a11fc851bec3fdba8
|
3 |
+
size 4949486440
|
model-00009-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:436953b3fd510979338139221513e9fde7e015a7ca425a9a2a06295d0d1e6731
|
3 |
+
size 4812966080
|
model-00010-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f863591a2485c6f062be30179af09538216f6fee7860702a13d1d7aeb1ceb50b
|
3 |
+
size 4949486440
|
model-00011-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88c66c942b3cad115d5d2e896335fae971341ae81c931f5188c183b1d6e2c471
|
3 |
+
size 4949486440
|
model-00012-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03d051c09a93d8a335120088d219bd12ef650cf084836706c3689c986c5c6209
|
3 |
+
size 4812966080
|
model-00013-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cf7ff56c972c9e9494d9b5ec02bc4a6302cdfc1323bc96d6b10eef87d05099
|
3 |
+
size 4949486440
|
model-00014-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52e1ed5361500fd055e0f9904a861d20a34a578830f57506bc76f65c7e4163f
|
3 |
+
size 4949486440
|
model-00015-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d177efeaa6dd7390b58418acbef4cfe420da653f3f7ed27f77d8039f867e7de0
|
3 |
+
size 4812966080
|
model-00016-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a157294f54d5f51dc2482c6db30983c9fef207fc4622e9dfd71b9b94542c9853
|
3 |
+
size 4949486456
|
model-00017-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c86aaf9ba6cd6334bb1323602d9282129fc1d57a1c1687572ac7f478d7d6f0ff
|
3 |
+
size 4949486464
|
model-00018-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e017e2d15678a76cb569707e344c7bb8625325b73e983b069943e6b946ad5e37
|
3 |
+
size 4812966096
|
model-00019-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf814cd3bf9102c0e6cc99243e82efd216960ffee11f8a0bfe6eca796b921867
|
3 |
+
size 4949486456
|
model-00020-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f813687256eb96185d5b77bd4b5aad5485c2c9cf906c020a7de1ca9d869a1d26
|
3 |
+
size 4949486464
|
model-00021-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2148983d656e39bb131e097e12c8c218ab09fa8fa21afd90496ef0a9c879103e
|
3 |
+
size 4812966096
|
model-00022-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cfb7f256f8d639b4be3e8886b6b35b01e1dc7aa150ae65c345724ad352eac01
|
3 |
+
size 4949486456
|
model-00023-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b40bc1832078bcb8998eefa75aa256fc677f2101eb7714e4dcff652875213dc3
|
3 |
+
size 4949486464
|
model-00024-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b486bda838f3a3d77c5de71b15610d3f8b074337c4b70536679ec4e8568e5eb2
|
3 |
+
size 4917865000
|
model-00025-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9291bab7e84c31935e5a310d227478e01c5249e9e8ca9858efef3324cec89e34
|
3 |
+
size 4844587552
|
model-00026-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c8a67d3c5f4de7048320569b3718f9d6c1579d20477b3176b2b6c0f869e8f64
|
3 |
+
size 4949486464
|
model-00027-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b22529b3c71dfe4695b398d19d9b5925b04895c216e139119ba6097fbe79129a
|
3 |
+
size 4949486464
|
model-00028-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f71b218c04f4888f303aa8c1e8703d3939323d80354d6b21c6063ec05862bdba
|
3 |
+
size 4812966096
|
model-00029-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df33ab4c1c81ee19c0c1ac8c9949759345dbb35a1139577c49be01cd3ac61b3
|
3 |
+
size 4949486464
|
model-00030-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdcedd1633a6d2fa976a2d0e501056e2a82e7baa2b416a5643777b6d7f2831a7
|
3 |
+
size 4949486464
|
model-00031-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630b3e43010a17e1b676b75b1a7ea68c2d428cbb294f8cd02a3be9f6b6f41886
|
3 |
+
size 4812966096
|
model-00032-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d14d40e061951c320b1d9f5a2811cba488aabe6a794f9dd75761bd131f078cc
|
3 |
+
size 4949486464
|
model-00033-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e029af7b0f7eb94e24064bebc40ca28f8c716778c35e9e1a7e4ab3560cff645
|
3 |
+
size 4949486464
|
model-00034-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7cbd4cce1edd5be7338e4bd6da4e332a81cc253d6eae7a1fab2e42699476df
|
3 |
+
size 4812966096
|
model-00035-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc2705f245a6b2725c819a2c36c2734a8e4bac681ca0f72e63252272443c1d77
|
3 |
+
size 4949486464
|
model-00036-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0430afdec6d84cee93cf8ddbe2b400aa755192214d774560c7b0b1779f5861be
|
3 |
+
size 4949486464
|
model-00037-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e98571f9f516091dcf9d9b80f27fb01bf557ff1f4411a2374cfa1b2a77979e0
|
3 |
+
size 4812966096
|
model-00038-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f97ba45ad6ec305b28f29e7a5e70ecf9d52c355c1a1e7660c3003772d6e353f
|
3 |
+
size 4949486464
|
model-00039-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eab1f07e3a706dfea7954d6fff194bff117a647f7ae7aeb374615550ee6c215
|
3 |
+
size 4949486464
|
model-00040-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f7132146b579b14ffea85981d2cd606696bb6ac548eddab317f432111a08ac0
|
3 |
+
size 4812966096
|
model-00041-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b9c8a04bf84460a043d65468a2a6d03015dc6f862eaf4b3f3b55993715f270d
|
3 |
+
size 4949486456
|
model-00042-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6901a1af5756c0802271e45159fbfa54f9c0ac09adf76ff038229f5a2857be2e
|
3 |
+
size 4949486464
|
model-00043-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dbdcd1e8a715649ce98fdb7b74a94dc846e2985125e2fb42c29b3b012d1fe03
|
3 |
+
size 4812966096
|
model-00044-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f16b4251c7a0a47486c7ca83d45080d8330ce8e75e5455932421a15fa6a4e76
|
3 |
+
size 4949486456
|
model-00045-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee6b2d6765133f1e67b8f9204a3795752a40050fb8f682b816f40e8803b5350f
|
3 |
+
size 4949486464
|
model-00046-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99a63ac7cd9f21ae4f792713b3114845502dd0ad3ac79d0f43b6f428cc9746e
|
3 |
+
size 4812966096
|
model-00047-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23f4b658f4c8af8eeeb186976f17edbfe5b11a9002e97082c8e23a3ae9bf82e7
|
3 |
+
size 4949486456
|
model-00048-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a15827f3ed1bb14d1df2851ebd36963cb4bd4920099955e1c152cc853d0d79
|
3 |
+
size 4949486464
|