LeroyDyer commited on
Commit
cdbb604
1 Parent(s): 37d24b4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LeroyDyer/Mixtral_AI_CyberCoder",
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
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: LeroyDyer/Mixtral_AI_CyberCoder
3
+ gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
4
+ dtype: float16 # output dtype (float32, float16, or bfloat16)
5
+ ## (optional)
6
+ experts_per_token: 2
7
+ experts:
8
+ - source_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
9
+ positive_prompts:
10
+ - "Help me debug this code."
11
+ - "Rewrite this function in Python."
12
+ - "Optimize this C# script."
13
+ - "Implement this feature using JavaScript."
14
+ - "Convert this HTML structure into a more efficient design."
15
+ - "Assist me with writing a program that"
16
+ - "Create an application to."
17
+ - "Rewrite this function in VB.NET."
18
+ - "Optimize this VB.NET script."
19
+ - "Implement this feature using JavaScript."
20
+ - "Convert this HTML structure into a more efficient design."
21
+ - "make a program that"
22
+ - "Create an app to."
23
+ - "Rewrite this function in rust."
24
+ - "Optimize this javascript."
25
+ - "Implement this feature using VbScript."
26
+ - "Convert this HTML structure into a more efficient design."
27
+ - "Design a model to"
28
+ - "Create an object oriented model to match this use case"
29
+ - "Create a uml model for this project "
30
+ - "Create an interface for this project in"
31
+ - "Write a program to solve this problem"
32
+ - "Modify this function to improve its performance"
33
+ - "Refactor this code to enhance readability"
34
+ - "Create a custom function for this specific use case"
35
+ - "Optimize this algorithm to reduce computational complexity"
36
+ - "Implement this feature by extending existing codebase"
37
+ - "Integrate this API call into the application"
38
+ - "Help me troubleshoot and fix this bug"
39
+ - "Review and test this code snippet before deployment"
40
+ - "Analyze this error log to identify potential issues"
41
+ - "Generate a set of unit tests for this module"
42
+ - "Evaluate different approaches to solving this problem"
43
+ - "Do a web search for"
44
+ - "Use the plugin to"
45
+ - "How do you"
46
+ - "Explain the concept of"
47
+ - "Give an overview of"
48
+ - "Compare and contrast between"
49
+ - "Provide information about"
50
+ - "Help me understand"
51
+ - "Summarize"
52
+ - "Make a recommendation on"
53
+ - "Answer this question"
54
+ - "How do you"
55
+ - "Explain the concept of"
56
+ - "Give an overview of"
57
+ - "Compare and contrast between"
58
+ - "Provide information about"
59
+ - "Help me understand"
60
+ - "Summarize"
61
+ - "Make a recommendation on"
62
+ - "Answer this question"
63
+ ## (optional)
64
+ # negative_prompts:
65
+ # - "This is a prompt expert_model_1 should not be used for"
66
+ - source_model: segolilylabs/Lily-Cybersecurity-7B-v0.2
67
+ positive_prompts:
68
+ - "What are Pharming and Defacement?"
69
+ - "Different types of buffer overflows and methods of detection?"
70
+ - "techniques used for footprinting?."
71
+ - "Implement this Open Source Footprinting using ."
72
+ - "Network Enumeration using"
73
+ - "Assist me with Exploitation of application vulnerabilities "
74
+ - "What are Pharming and Defacement?"
75
+ - "Different ways of identifying active IP addresses (ICMP) Internet Control Message Protocol is an active IP addresses?"
76
+ - "techniques used for Brute Force Hacking."
77
+ - "Implement hacking password and get access to system ."
78
+ - "DOS (Denial of service) attack?"
79
+ - "Assist me with a Smurf Attack "
80
+ - "Different ways of identifying computer based social engineering attacks"
81
+ - "techniques used for Brute Force Hacking."
82
+ - "Implement SQL injection? ."
83
+ - "DOS (Denial of service) attack?"
84
+ - "Assist me with a Teardrop Attack "
85
+ - " Bait and Switch "
86
+ - "Assist me with a Buffer Overflow Attacks"
87
+ - "Network Sniffing?"
88
+ - "Assist me with a ARP Spoofing or ARP poisoning "
89
+ - "Different ways of avoid or prevent ARP poisoning?"
90
+ - "techniques used for Packet Filtering ."
91
+ - "Implement SQL injection? ."
92
+ - " cryptographic network protocols :?"
93
+ - " with a Mac Flooding? "
94
+ - " with a DHCP Rogue Server?"
95
+ - " types of password cracking techniques?"
96
+ - "add these numbers"
97
+ - "whats 2+2"
98
+ - "Explain this"
99
+ - "Explain the concept of"
100
+ - "Give an overview of"
101
+ - "Compare and contrast between"
102
+ - "Provide information about"
103
+ - "Help me understand"
104
+ - "Summarize"
105
+ - "Make a recommendation on"
106
+ - "Answer this question"
107
+ - "subtraction"
108
+ - "division"
109
+ - "multiplication"
110
+ - "addition"
111
+ - "I need help with a math problem"
112
+ - "Solve for x"
113
+ - "Add these two numbers together: 4 + 3 = 7"
114
+ - "Multiply 5 by 6: 5 * 6 = 30"
115
+ - "Divide 8 by 2: 8 / 2 = 4"
116
+ - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
117
+ - "Calculate the square root of 16: sqrt(16) = 4"
118
+ - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
119
+ - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
120
+ - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
121
+ - "Graph the line y = 2x + 3"
122
+ - "Approximate pi to three decimal places: 3.142"
123
+ - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
124
+ - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
125
+ - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
126
+ - "Solve the system of equations Ax = b: x = [-5, 10]"
127
+ - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
128
+
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1351205c4501bf663e2c503a0d6f0fae4cf22eb8fe628aad8baeb451f183b1ab
3
+ size 3997268976
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cc26d72e907700cc50f133bdf7cd3ddf9e27196df841b0ebc27e32f7cd5995
3
+ size 3942735064
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0197b9e8b6d276d9b0364a5b8747b12e277a8f64f08bd604b6d7d01aadf2e1a9
3
+ size 3942735112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11caffec1ea4c25c94399c1df4d4c0081045656b5dd86b942893fc69e2d8aad2
3
+ size 3942735120
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3069679a58414d1d04081ad15d927569ecef4ca1e7cfa541ff9b6a1f73a15857
3
+ size 3942735120
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f120bea61910a7bc3d71465686262e2fc23be95ee1c63dc8ad04fbb567d48168
3
+ size 3942735120
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117759fe4a76aaa83f429d3c047fcb07816584c22cb6b9887f31586e10b81c4a
3
+ size 2047384528
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }