dzakwan commited on
Commit
e89f82f
1 Parent(s): 3e90e5b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - mlabonne/AlphaMonarch-7B
10
+ - beowolx/CodeNinja-1.0-OpenChat-7B
11
+ - SanjiWatsuki/Kunoichi-DPO-v2-7B
12
+ - mlabonne/NeuralDaredevil-7B
13
+ base_model:
14
+ - mlabonne/AlphaMonarch-7B
15
+ - beowolx/CodeNinja-1.0-OpenChat-7B
16
+ - SanjiWatsuki/Kunoichi-DPO-v2-7B
17
+ - mlabonne/NeuralDaredevil-7B
18
+ ---
19
+
20
+ # dzakwan-MoE-4x7b-Beta
21
+
22
+ dzakwan-MoE-4x7b-Beta is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
23
+ * [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
24
+ * [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
25
+ * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
26
+ * [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B)
27
+
28
+ ## 🧩 Configuration
29
+
30
+ ```yaml
31
+ base_model: mlabonne/AlphaMonarch-7B
32
+ experts:
33
+ - source_model: mlabonne/AlphaMonarch-7B
34
+ positive_prompts:
35
+ - "chat"
36
+ - "assistant"
37
+ - "tell me"
38
+ - "explain"
39
+ - "I want"
40
+ - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
41
+ positive_prompts:
42
+ - "code"
43
+ - "python"
44
+ - "javascript"
45
+ - "programming"
46
+ - "algorithm"
47
+ - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
48
+ positive_prompts:
49
+ - "storywriting"
50
+ - "write"
51
+ - "scene"
52
+ - "story"
53
+ - "character"
54
+ - source_model: mlabonne/NeuralDaredevil-7B
55
+ positive_prompts:
56
+ - "reason"
57
+ - "math"
58
+ - "mathematics"
59
+ - "solve"
60
+ - "count"
61
+ ```
62
+
63
+ ## 💻 Usage
64
+
65
+ ```python
66
+ !pip install -qU transformers bitsandbytes accelerate
67
+
68
+ from transformers import AutoTokenizer
69
+ import transformers
70
+ import torch
71
+
72
+ model = "dzakwan/dzakwan-MoE-4x7b-Beta"
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained(model)
75
+ pipeline = transformers.pipeline(
76
+ "text-generation",
77
+ model=model,
78
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
79
+ )
80
+
81
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
82
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
83
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
84
+ print(outputs[0]["generated_text"])
85
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/AlphaMonarch-7B",
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": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.41.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: mlabonne/AlphaMonarch-7B
2
+ experts:
3
+ - source_model: mlabonne/AlphaMonarch-7B
4
+ positive_prompts:
5
+ - "chat"
6
+ - "assistant"
7
+ - "tell me"
8
+ - "explain"
9
+ - "I want"
10
+ - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
11
+ positive_prompts:
12
+ - "code"
13
+ - "python"
14
+ - "javascript"
15
+ - "programming"
16
+ - "algorithm"
17
+ - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
18
+ positive_prompts:
19
+ - "storywriting"
20
+ - "write"
21
+ - "scene"
22
+ - "story"
23
+ - "character"
24
+ - source_model: mlabonne/NeuralDaredevil-7B
25
+ positive_prompts:
26
+ - "reason"
27
+ - "math"
28
+ - "mathematics"
29
+ - "solve"
30
+ - "count"
model-00001-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f67893b876271f4f9cf830d44120e4334ddf0e098996d35879d51e4ce51ffde
3
+ size 1933849888
model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb11383ca4f767dc6c9bb1616de44518fc1010a49361960f99d07b8ba40b9a1
3
+ size 1996490936
model-00003-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4f72b9bc969f6490d9faa354a1a22d4404c477b5a0a0280f8242718f5d2b43
3
+ size 1996490936
model-00004-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5f1a257c912af3b7bd7cd9f2a37a45efc598f5bf5f8d55db062e12b1ca9c33
3
+ size 1996490952
model-00005-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4d6cd5d44d3b95e2530810b8aff5690d08ff1be783703ba2340682e4ee0b82
3
+ size 1996490952
model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0961beed2fd3a4fa202ab6957c75d989f726921fcb6e06a137e7eb8020192d48
3
+ size 1996490952
model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768ee83731f662df1b3e604df22b818a1aa705e68500a2ccb20554da4d166a5d
3
+ size 1996490952
model-00008-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7a6dd203d3bf68d4de3b031bc01cdffc6b864c43907634d2bfbe2b011cb3a0b
3
+ size 1996490944
model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593c4b3ab85498e98fc99bbd9c7025ae967d4df0567c68d6783f0a3dd070021e
3
+ size 1996490936
model-00010-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb4ea7b75dc418a6eee4a5c67044c3870fcfcec404cec79e8d907e8b2707d8c
3
+ size 1996490936
model-00011-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87301ed26fca3f490a89057d9daff3a32b45724b90bd1d5dd84eb19c63d7751b
3
+ size 1996490944
model-00012-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d123743649a29707e398bbeb126d212d355d78c48b1e48b243f60f3e4ae43cd
3
+ size 1996490952
model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669b1ba7c288cf518b2d1b13dc50f7cb6ada9d5378f56bf15c94632b638bfaf9
3
+ size 1996490952
model-00014-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dca71cef31d5f6b418fa0c920e6228472c643caea7402fe105556f1078843f
3
+ size 1996490952
model-00015-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e0409ce2f8ff4f03cf4852b135bb83dc984a48322293f7511c17c3ca2da73a
3
+ size 1996490952
model-00016-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa34694695561b8c4dd1230f3017b89a36c597a134c78fe90aad640cd46172a7
3
+ size 1996490936
model-00017-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ee23d3df35127f7ee37d5a35a98f87eb51f3eba7c89e613f6aef101ec7dee2
3
+ size 1996490936
model-00018-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d22370626ab6f2c5394c895c88393435f749721648f9b3d3b9a63717afdbcf7
3
+ size 1996490936
model-00019-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330303d8b82c49c593e28c05b1dcc84ac44f8aa3c391818737425c4b8bee180f
3
+ size 1996490952
model-00020-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8589ec0c4dd2b26deed1713b1b8b5ada61e223ea0a8f2ec5b2c834014bca4bdc
3
+ size 1996490952
model-00021-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7705064a68aef1655dad177e17b705aa7ff5b27dfaa299a4b6f723da7462b680
3
+ size 1996490952
model-00022-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4913cb14c4fda9411549ef58f07b023df410879cd5964fd8775c85c890f294b3
3
+ size 1996490952
model-00023-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c1b96319abeaecd8729758b70c206bf3e3827e11868954003ad1b2586c5d77
3
+ size 1996757384
model-00024-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bf81d98590fb28ef0b301f08567fad6cb0bddfa65a4d928ca91385458dc520
3
+ size 1979723896
model-00025-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7563778d8fee18659327cce10f4312e03c802e0fd528b86a2da8fe29f0014f67
3
+ size 470815920
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 8192,
41
+ "pad_token": "<s>",
42
+ "padding_side": "left",
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
+ }