Commit
•
c639568
1
Parent(s):
a9fcca5
Upload folder using huggingface_hub
Browse files- README.md +63 -0
- config.json +33 -0
- mergekit_config.yml +17 -0
- model-00001-of-00028.safetensors +3 -0
- model-00002-of-00028.safetensors +3 -0
- model-00003-of-00028.safetensors +3 -0
- model-00004-of-00028.safetensors +3 -0
- model-00005-of-00028.safetensors +3 -0
- model-00006-of-00028.safetensors +3 -0
- model-00007-of-00028.safetensors +3 -0
- model-00008-of-00028.safetensors +3 -0
- model-00009-of-00028.safetensors +3 -0
- model-00010-of-00028.safetensors +3 -0
- model-00011-of-00028.safetensors +3 -0
- model-00012-of-00028.safetensors +3 -0
- model-00013-of-00028.safetensors +3 -0
- model-00014-of-00028.safetensors +3 -0
- model-00015-of-00028.safetensors +3 -0
- model-00016-of-00028.safetensors +3 -0
- model-00017-of-00028.safetensors +3 -0
- model-00018-of-00028.safetensors +3 -0
- model-00019-of-00028.safetensors +3 -0
- model-00020-of-00028.safetensors +3 -0
- model-00021-of-00028.safetensors +3 -0
- model-00022-of-00028.safetensors +3 -0
- model-00023-of-00028.safetensors +3 -0
- model-00024-of-00028.safetensors +3 -0
- model-00025-of-00028.safetensors +3 -0
- model-00026-of-00028.safetensors +3 -0
- model-00027-of-00028.safetensors +3 -0
- model-00028-of-00028.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- zhengr/MixTAO-7Bx2-MoE-v8.1
|
7 |
+
- allknowingroger/JupiterINEX12-12B-MoE
|
8 |
+
base_model:
|
9 |
+
- zhengr/MixTAO-7Bx2-MoE-v8.1
|
10 |
+
- allknowingroger/JupiterINEX12-12B-MoE
|
11 |
+
---
|
12 |
+
|
13 |
+
# MultiMash8-13B-slerp
|
14 |
+
|
15 |
+
MultiMash8-13B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
|
17 |
+
* [allknowingroger/JupiterINEX12-12B-MoE](https://huggingface.co/allknowingroger/JupiterINEX12-12B-MoE)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
25 |
+
layer_range: [0, 32]
|
26 |
+
- model: allknowingroger/JupiterINEX12-12B-MoE
|
27 |
+
layer_range: [0, 32]
|
28 |
+
merge_method: slerp
|
29 |
+
base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
30 |
+
parameters:
|
31 |
+
t:
|
32 |
+
- filter: self_attn
|
33 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
+
- filter: mlp
|
35 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
+
- value: 0.5
|
37 |
+
dtype: bfloat16
|
38 |
+
```
|
39 |
+
|
40 |
+
## 💻 Usage
|
41 |
+
|
42 |
+
```python
|
43 |
+
!pip install -qU transformers accelerate
|
44 |
+
|
45 |
+
from transformers import AutoTokenizer
|
46 |
+
import transformers
|
47 |
+
import torch
|
48 |
+
|
49 |
+
model = "allknowingroger/MultiMash8-13B-slerp"
|
50 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
51 |
+
|
52 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
53 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
54 |
+
pipeline = transformers.pipeline(
|
55 |
+
"text-generation",
|
56 |
+
model=model,
|
57 |
+
torch_dtype=torch.float16,
|
58 |
+
device_map="auto",
|
59 |
+
)
|
60 |
+
|
61 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
62 |
+
print(outputs[0]["generated_text"])
|
63 |
+
```
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 2,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"pad_token_id": 2,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"router_aux_loss_coef": 0.001,
|
25 |
+
"router_jitter_noise": 0.0,
|
26 |
+
"sliding_window": null,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.41.0",
|
30 |
+
"unsloth_version": "2024.1",
|
31 |
+
"use_cache": false,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
5 |
+
layer_range: [0, 32]
|
6 |
+
- model: allknowingroger/JupiterINEX12-12B-MoE
|
7 |
+
layer_range: [0, 32]
|
8 |
+
merge_method: slerp
|
9 |
+
base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
10 |
+
parameters:
|
11 |
+
t:
|
12 |
+
- filter: self_attn
|
13 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
+
- filter: mlp
|
15 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
+
- value: 0.5
|
17 |
+
dtype: bfloat16
|
model-00001-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd38b0decec4353ffbe4c645fc14e7862fd289b3f5ca88933047681fb6cbced2
|
3 |
+
size 994050792
|
model-00002-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:453e3f08d0c0834a42a0cfbf3363494e09ba1f47575f8cf0e83ce8dbc2c070ca
|
3 |
+
size 906004176
|
model-00003-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df35941c8a9fd80f5a62e3f9c769240122e2d814b67cf350d4c9b6c7d84614f6
|
3 |
+
size 989923840
|
model-00004-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcee8cc2ae76cc7ba1c50200a0dab592607c3e7a73e13d89b9c7266c42e2641b
|
3 |
+
size 906004192
|
model-00005-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a12d97e63a03fbb4b89075da8e41dab1e316d32a2421a109319448f4a89ff08f
|
3 |
+
size 906004192
|
model-00006-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:483fa022bd910cb2155bca34542bdecbaa1bd43358664b541257c771a74d811e
|
3 |
+
size 906004192
|
model-00007-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dee1087ab11b4016b68dd0fc896b97566e837dd664d3908488839e4b791d0437
|
3 |
+
size 906004192
|
model-00008-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c6432d22297ac55b909381d9458ccfaca3e4bd7f56381ee1972ff335ed2c134
|
3 |
+
size 906004192
|
model-00009-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa4aa6a0cb92566ad09213efe0d09197bda8566c1e87dbb325f3a6b0fd61c982
|
3 |
+
size 989923848
|
model-00010-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb40a009943ebdd3f2509ba9bc8b6176803b1aea3c2368a58ec5add8e0bbc949
|
3 |
+
size 906004192
|
model-00011-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3cce9ad27434b259927f2cb447c288d8c520d13c69f5ce5edffdbfb526e43fd
|
3 |
+
size 906004184
|
model-00012-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bf27ebde930ce901e0cae3e99ce8fb5b44deaa36f085a415e9131730ba81b67
|
3 |
+
size 906004176
|
model-00013-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a1b7a98bca874494f6a2691bd7277c683ab4eaf87a27b3850058f7b2139070a
|
3 |
+
size 906004192
|
model-00014-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a4abb3ef8f58084e64852ba79ffe52bede47a5e982a6d545de33d10e040faa4
|
3 |
+
size 906004192
|
model-00015-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dbbcf8e3125570e88d6189b7bfba36d30f5e08221f247ce35a32a64d7458509
|
3 |
+
size 989923848
|
model-00016-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f343b506eaf2c02628b286f5e072ffe4238d0743be0f663e5bca63a47a5460e5
|
3 |
+
size 906004192
|
model-00017-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a1db629fc2d5800b2e99af98b7ad93b20805eee3cfc2c98742173dcb543998f
|
3 |
+
size 906004192
|
model-00018-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e31f69f17d89343a611d892664b3d638ea0341b3bff1150c457963cd4632ef70
|
3 |
+
size 906004192
|
model-00019-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7907aae4cde55f785bcdd93034a8e63298f48bf58e46fba247c45812a8077bb9
|
3 |
+
size 906004192
|
model-00020-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be0af9a169a435991d784f14b396226f8ee3070322c071d28c386751dcb6558d
|
3 |
+
size 906004192
|
model-00021-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1135d517a6ee24e21d015a5c27277a5dac2793a1260836d1f8b2d8fef4818e8c
|
3 |
+
size 989923832
|
model-00022-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdedee827dfb172e74a57c3c881118da78ba04a91d624ec2885d70db5a734dd
|
3 |
+
size 906004192
|
model-00023-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9264520de4ecdcc760f328a56fec53aa3b1e91c8a9243274cc11d1cd87a5ea3e
|
3 |
+
size 906004184
|
model-00024-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:613d79275c16bcb4bb87ebc656350e7dc480e45d2f72c024425c2337f9aed328
|
3 |
+
size 906004176
|
model-00025-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dba0e362af7775f7551f58a8f21ca9aea2036f9402d32a5bc9bdc68b098c07ea
|
3 |
+
size 906004176
|
model-00026-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a168ad7e938ab3456655d38580373d7e099cbd057cc1f24c280ac7ed6911f74
|
3 |
+
size 906004176
|
model-00027-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab4073d24151f95cabc956fde8b9e32020b3cee98eae37f3d1e0dde9f1b337ad
|
3 |
+
size 989923824
|
model-00028-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a8d32648b96dc83ebe89a82cf79bb80babd29d8d013f038d9c742bae9a3b83c
|
3 |
+
size 788571816
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00002-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00014-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00016-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00017-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00018-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00022-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00023-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00026-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [
|
32 |
+
"<unk>",
|
33 |
+
"<s>",
|
34 |
+
"</s>"
|
35 |
+
],
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 255,
|
41 |
+
"pad_token": "<s>",
|
42 |
+
"padding_side": "right",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"split_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": true
|
49 |
+
}
|