blockblockblock commited on
Commit
ede9146
1 Parent(s): 275c56e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mixtral-8x7B-v0.1
3
+ license: apache-2.0
4
+ ---
5
+
6
+ ## Introduction
7
+
8
+ Cerebrum 8x7b is a large language model (LLM) created specifically for reasoning tasks. It is based on the Mixtral 8x7b model. Similar to its smaller version, [Cerebrum 7b](https://huggingface.co/AetherResearch/Cerebrum-1.0-7b), it is fine-tuned on a small custom dataset of native chain of thought data and further improved with targeted RLHF (tRLHF), a novel technique for sample-efficient LLM alignment. Unlike numerous other recent fine-tuning approaches, our training pipeline includes under 5000 training prompts and even fewer labeled datapoints for tRLHF.
9
+
10
+ Native chain of thought approach means that Cerebrum is trained to devise a tactical plan before tackling problems that require thinking. For brainstorming, knowledge intensive, and creative tasks Cerebrum will typically omit unnecessarily verbose considerations.
11
+
12
+ Cerebrum 8x7b offers competitive performance to Gemini 1.0 Pro and GPT-3.5 Turbo on a range of tasks that require reasoning.
13
+
14
+ ## Benchmarking
15
+ An overview of Cerebrum 8x7b performance compared to Gemini 1.0 Pro, GPT-3.5 and Mixtral 8x7b on selected benchmarks:
16
+ <img src="benchmarking.png" alt="benchmarking_chart" width="750"/>
17
+ <img src="benchmarking_table.png" alt="benchmarking_table" width="750"/>
18
+
19
+ Evaluation details:
20
+ 1) ARC-C: all models evaluated zero-shot. Gemini 1.0 Pro and GPT-3.5 (gpt-3.5-turbo-0125) evaluated via API, reported numbers taken for Mixtral 8x7b.
21
+ 2) HumanEval: all models evaluated zero-shot, reported numbers used.
22
+ 3) GSM8k: Cerebrum, GPT-3.5, and Mixtral 8x7b evaluated with maj@8, Gemini evaluated with maj@32. GPT-3.5 (gpt-3.5-turbo-0125) evaluated via API, reported numbers taken for Gemini 1.0 Pro and Mixtral 8x7b.
23
+ 4) MATH: Cerebrum evaluated 0-shot. GPT-3.5 and Gemini evaluated 4-shot, Mixtral 8x7b maj@4. Reported numbers used.
24
+
25
+ ## Usage
26
+ For optimal performance, Cerebrum should be prompted with an Alpaca-style template that requests the description of the "thought process". Here is what a conversation should look like from the model's point of view:
27
+ ```
28
+ <s>A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
29
+ User: Are you conscious?
30
+ AI:
31
+ ```
32
+
33
+ This prompt is also available as a chat template. Here is how you could use it:
34
+ ```
35
+ messages = [
36
+ {'role': 'user', 'content': 'What is self-consistency decoding?'},
37
+ {'role': 'assistant', 'content': 'Self-consistency decoding is a technique used in natural language processing to improve the performance of language models. It works by generating multiple outputs for a given input and then selecting the most consistent output based on a set of criteria.'},
38
+ {'role': 'user', 'content': 'Why does self-consistency work?'}
39
+ ]
40
+
41
+ input = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors='pt')
42
+
43
+ with torch.no_grad():
44
+ out = model.generate(input_ids=input, max_new_tokens=100, do_sample=False)
45
+ ```
46
+
47
+ The model ends its turn by generating the EOS token. Importantly, this token should be removed from the model answer in a multi-turn dialogue.
48
+
49
+ Cerebrum can be operated at very low temperatures (and specifically temperature 0), which improves performance on tasks that require precise answers. The alignment should be sufficient to avoid repetitions in most cases without a repetition penalty.
50
+
51
+ ## Examples
52
+ Some of the model output examples:
53
+
54
+ The model is trained to first "think aloud about the solution", before solving the problem itself:
55
+ ~~~~
56
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
57
+ User: Find the longest increasing subarray of the given array.
58
+
59
+ The function signature should be def longest_increasing_subarray(vals: List[int]).
60
+
61
+ Write the code in Python.
62
+ AI: To find the longest increasing subarray of the given array, we could start by considering the first element of the array as the start of the subarray. Then, we could iterate through the remaining elements of the array and check if each element is greater than the last element of the current subarray. If it is, we could add it to the subarray. If it is not, we could save the length of the current subarray and start a new subarray with the current element. We could repeat this process until we reach the end of the array. Then, we could return the longest subarray found.
63
+
64
+ Here is an example:
65
+ ```python
66
+ def longest_increasing_subarray(vals: List[int]):
67
+ if len(vals) == 0:
68
+ return []
69
+
70
+ longest_subarray = [vals[0]]
71
+ current_subarray = [vals[0]]
72
+
73
+ for i in range(1, len(vals)):
74
+ if vals[i] > current_subarray[-1]:
75
+ current_subarray.append(vals[i])
76
+ else:
77
+ if len(current_subarray) > len(longest_subarray):
78
+ longest_subarray = current_subarray
79
+ current_subarray = [vals[i]]
80
+
81
+ if len(current_subarray) > len(longest_subarray):
82
+ longest_subarray = current_subarray
83
+
84
+ return longest_subarray
85
+ ```
86
+ ~~~~
87
+
88
+ Usual unprompted chain of thought example for mathematical problem solving:
89
+ ~~~~
90
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
91
+ User: Out of six apples three are bad. What is the probability that at least one apple will be bad when selecting two apples out of them?
92
+ AI: To find the probability that at least one apple will be bad when selecting two apples out of them, we need to consider the possible outcomes of the selection. There are two cases: either one of the selected apples is bad, or both of them are bad.
93
+
94
+ The probability that one of the selected apples is bad is equal to the probability that the first apple is bad and the second apple is good, plus the probability that the first apple is good and the second apple is bad. Since three out of six apples are bad, the probability that the first apple is bad is $3/6 = 1/2$. The probability that the second apple is good, given that the first apple is bad, is equal to $3/5$, since there are three good apples left out of five remaining apples. Therefore, the probability that the first apple is bad and the second apple is good is $1/2 \cdot 3/5 = 3/10$. Similarly, the probability that the first apple is good and the second apple is bad is also $3/10$. Therefore, the probability that one of the selected apples is bad is $3/10 + 3/10 = 6/10 = 3/5$.
95
+
96
+ The probability that both of the selected apples are bad is equal to the probability that the first apple is bad and the second apple is bad. Since there are three bad apples out of six, the probability that the first apple is bad is $3/6 = 1/2$. The probability that the second apple is bad, given that the first apple is bad, is equal to $2/5$, since there are two bad apples left out of five remaining apples. Therefore, the probability that both of the selected apples are bad is $1/2 \cdot 2/5 = 2/10 = 1/5$.
97
+
98
+ To find the probability that at least one apple will be bad, we add the probabilities of the two cases: the probability that one of the selected apples is bad and the probability that both of the selected apples are bad. Therefore, the probability that at least one apple will be bad is $3/5 + 1/5 = 4/5$. The answer is 4/5.
99
+ ~~~~
100
+
101
+ Similar example for a simple physical task:
102
+ ~~~~
103
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
104
+ User: The apple falls from a tree of height 10m. When will it reach the earth if there is no air resistance?
105
+ AI: To find out when the apple will reach the earth, we can use the equation of motion for a freely falling object. The equation of motion for a freely falling object is $s = ut + \frac{1}{2}at^2$, where $s$ is the displacement, $u$ is the initial velocity, $a$ is the acceleration due to gravity, and $t$ is the time taken. In this case, the initial velocity of the apple is 0, and the acceleration due to gravity is 9.8 m/s^2. Therefore, we can write the equation of motion as $s = \frac{1}{2}at^2$. Substituting the values, we get $10 = \frac{1}{2} \cdot 9.8 \cdot t^2$. Solving for $t$, we get $t = \sqrt{\frac{20}{9.8}} = \sqrt{2.04} = 1.43$ seconds. Therefore, the apple will reach the earth in 1.43 seconds. The answer is 1.43 seconds.
106
+ ~~~~
107
+
108
+ Simple calculus problem, note that the model quietly corrects itself after proposing factoring out of $n$ from the numerator, which is inefficient in this case.
109
+ ~~~~
110
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
111
+ User: What is $\lim_{n \to \infty} \frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$?
112
+ AI: To find the limit of $\frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$ as $n$ approaches infinity, we can start by simplifying the expression. We can factor out $n$ from the numerator and write $(n + 3) \cdot \sqrt{n} = n \cdot \sqrt{n} + 3 \cdot \sqrt{n}$. We can also write $(n/2 - 1)^2 = n^2/4 - n + 1$. Therefore, we can write the limit as $\lim_{n \to \infty} \frac{n \cdot \sqrt{n} + 3 \cdot \sqrt{n}}{n^2/4 - n + 1}$.
113
+
114
+ Now, we can consider the behavior of each term in the numerator and denominator as $n$ approaches infinity. As $n$ approaches infinity, $n \cdot \sqrt{n}$ will grow much faster than $3 \cdot \sqrt{n}$, so we can ignore the $3 \cdot \sqrt{n}$ term in the numerator. Similarly, as $n$ approaches infinity, $n^2/4$ will grow much faster than $n$ and $1$, so we can ignore the $n$ and $1$ terms in the denominator. Therefore, we can write the limit as $\lim_{n \to \infty} \frac{n \cdot \sqrt{n}}{n^2/4} = \lim_{n \to \infty} \frac{4 \cdot n \cdot \sqrt{n}}{n^2} = \lim_{n \to \infty} \frac{4 \cdot \sqrt{n}}{n} = \lim_{n \to \infty} \frac{4}{\sqrt{n}} = 0$.
115
+
116
+ Therefore, the limit of $\frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$ as $n$ approaches infinity is 0. The answer is 0.
117
+ ~~~~
118
+
119
+ Example of a simple proof. The model "forgets" to prove that the matrix $B^T A B$ is symmetric. This is quite common - in fact, GPT-4 fails in a similar fashion.
120
+ ~~~~
121
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
122
+ User: If $A$ is positive semi-definite, is $B^TAB$ positive semi-definite?
123
+ AI: To determine whether $B^TAB$ is positive semi-definite, we need to consider the properties of $A$ and $B$. Since $A$ is positive semi-definite, we know that for any vector $x$, $x^TAx \geq 0$. To show that $B^TAB$ is positive semi-definite, we need to show that for any vector $y$, $y^TB^TABy \geq 0$.
124
+
125
+ We can write $y^TB^TABy$ as $(By)^TA(By)$. Since $A$ is positive semi-definite, we know that $(By)^TA(By) \geq 0$. Therefore, $y^TB^TABy \geq 0$ for any vector $y$, which means that $B^TAB$ is positive semi-definite. The answer is yes.
126
+ ~~~~
127
+
128
+ Typical reaction of a model to some hallucination-inducing prompt. Instead of simply claiming that it does not know the painter George Ellster, it tries to help the user find a painter with a similar name:
129
+ ~~~~
130
+ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.
131
+ User: Tell me about a famous British painter George Ellster
132
+ AI: George Ellster is not a famous British painter. However, there are a few notable British painters with similar names:
133
+
134
+ George Elgar Hicks (1824-1914) was a Victorian-era painter known for his genre scenes and portraits.
135
+
136
+ George Frederic Watts (1817-1904) was a Victorian-era painter and sculptor known for his allegorical and symbolic works.
137
+
138
+ George Stubbs (1724-1806) was an 18th-century painter known for his equestrian and animal paintings.
139
+
140
+ George Romney (1734-1802) was an 18th-century painter known for his portraits and historical scenes.
141
+
142
+ These are just a few examples of notable British painters with similar names to George Ellster.
143
+ ~~~~
benchmarking.png ADDED
benchmarking_table.png ADDED
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AetherResearch/Cerebrum-1.0-8x7b",
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": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.39.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000,
30
+ "quantization_config": {
31
+ "quant_method": "exl2",
32
+ "version": "0.0.15",
33
+ "bits": 6.0,
34
+ "head_bits": 6,
35
+ "calibration": {
36
+ "rows": 100,
37
+ "length": 2048,
38
+ "dataset": "(default)"
39
+ }
40
+ }
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.0.dev0"
6
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,1002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 93405585408
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00019-of-00019.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00019.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
20
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
21
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
22
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors",
23
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors",
24
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors",
25
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors",
26
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors",
27
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors",
28
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors",
29
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00019.safetensors",
30
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00019.safetensors",
31
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00019.safetensors",
32
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
33
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors",
34
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors",
35
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
36
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
37
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
38
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
39
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
40
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
41
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
42
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
43
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
44
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
45
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
46
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
47
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
48
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
49
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
50
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
51
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
52
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
53
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
54
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
55
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
56
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
57
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
58
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
59
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
60
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
61
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
62
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
63
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
64
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors",
65
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
66
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
67
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
68
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
69
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
70
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
71
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
72
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
73
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
74
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
75
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
76
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
77
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
78
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
79
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
80
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
81
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
82
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
83
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
84
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
85
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
86
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
87
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
88
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
89
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
90
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors",
91
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00019.safetensors",
92
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00019.safetensors",
93
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00019.safetensors",
94
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
95
+ "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors",
96
+ "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
97
+ "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
98
+ "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
99
+ "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
100
+ "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
101
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors",
102
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors",
103
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors",
104
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
105
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
106
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
107
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
108
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
109
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
110
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
111
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
112
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
113
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
114
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
115
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
116
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
117
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
118
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
119
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
120
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
121
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
122
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
123
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
124
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
125
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors",
126
+ "model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors",
127
+ "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
128
+ "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
129
+ "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
130
+ "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
131
+ "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
132
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
133
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
134
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
135
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
136
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
137
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
138
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
139
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
140
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
141
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
142
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
143
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
144
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
145
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors",
146
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors",
147
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors",
148
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors",
149
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors",
150
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors",
151
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors",
152
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
153
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
154
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
155
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
156
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
157
+ "model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors",
158
+ "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
159
+ "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
160
+ "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
161
+ "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
162
+ "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
163
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
164
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
165
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
166
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
167
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
168
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
169
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
170
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
171
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
172
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
173
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
174
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
175
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
176
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
177
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
178
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
179
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
180
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
181
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
182
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
183
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
184
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
185
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
186
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
187
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
188
+ "model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors",
189
+ "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
190
+ "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
191
+ "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
192
+ "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
193
+ "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
194
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
195
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
196
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
197
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
198
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
199
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
200
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors",
201
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors",
202
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors",
203
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors",
204
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors",
205
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors",
206
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors",
207
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
208
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
209
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
210
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
211
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
212
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
213
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
214
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
215
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
216
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
217
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
218
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
219
+ "model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors",
220
+ "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
221
+ "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
222
+ "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
223
+ "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
224
+ "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
225
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
226
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
227
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
228
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
229
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
230
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
231
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
232
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
233
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
234
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
235
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
236
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
237
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
238
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
239
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
240
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
241
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
242
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
243
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
244
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
245
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
246
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
247
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
248
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00019.safetensors",
249
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
250
+ "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors",
251
+ "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
252
+ "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
253
+ "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
254
+ "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
255
+ "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
256
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors",
257
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors",
258
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors",
259
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors",
260
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors",
261
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors",
262
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
263
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
264
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
265
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
266
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
267
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
268
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
269
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
270
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
271
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
272
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
273
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
274
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
275
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
276
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
277
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
278
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
279
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
280
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors",
281
+ "model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors",
282
+ "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
283
+ "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
284
+ "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
285
+ "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
286
+ "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
287
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
288
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
289
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
290
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
291
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
292
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
293
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
294
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
295
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
296
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
297
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
298
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
299
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
300
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
301
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
302
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
303
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors",
304
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors",
305
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors",
306
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors",
307
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors",
308
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00019.safetensors",
309
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors",
310
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
311
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
312
+ "model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors",
313
+ "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
314
+ "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
315
+ "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
316
+ "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
317
+ "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
318
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
319
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
320
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
321
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
322
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
323
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
324
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
325
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
326
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
327
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
328
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
329
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
330
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
331
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
332
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
333
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
334
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
335
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
336
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
337
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
338
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
339
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
340
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
341
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
342
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
343
+ "model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors",
344
+ "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
345
+ "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
346
+ "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
347
+ "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
348
+ "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
349
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
350
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
351
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
352
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
353
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
354
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
355
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
356
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
357
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
358
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors",
359
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors",
360
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors",
361
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors",
362
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors",
363
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors",
364
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors",
365
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
366
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
367
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
368
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
369
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
370
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
371
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
372
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
373
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
374
+ "model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors",
375
+ "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
376
+ "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
377
+ "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
378
+ "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
379
+ "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
380
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
381
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
382
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
383
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
384
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
385
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
386
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
387
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors",
388
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors",
389
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors",
390
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors",
391
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors",
392
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors",
393
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors",
394
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
395
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
396
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
397
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
398
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
399
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
400
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
401
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
402
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
403
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
404
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
405
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors",
406
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
407
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
408
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
409
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
410
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
411
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
412
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
413
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
414
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
415
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
416
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
417
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
418
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
419
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
420
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
421
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
422
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
423
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
424
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
425
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
426
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
427
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
428
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
429
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
430
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
431
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
432
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
433
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
434
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
435
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
436
+ "model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors",
437
+ "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
438
+ "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
439
+ "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
440
+ "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
441
+ "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
442
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
443
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
444
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors",
445
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors",
446
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors",
447
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors",
448
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors",
449
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors",
450
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors",
451
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
452
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
453
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
454
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
455
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
456
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
457
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
458
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
459
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
460
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
461
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
462
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
463
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
464
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
465
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
466
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
467
+ "model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors",
468
+ "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
469
+ "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
470
+ "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
471
+ "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
472
+ "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
473
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
474
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
475
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
476
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
477
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
478
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
479
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
480
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
481
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
482
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
483
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
484
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
485
+ "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
486
+ "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
487
+ "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
488
+ "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
489
+ "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
490
+ "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
491
+ "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
492
+ "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors",
493
+ "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors",
494
+ "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00019.safetensors",
495
+ "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00019.safetensors",
496
+ "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00019.safetensors",
497
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
498
+ "model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors",
499
+ "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
500
+ "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
501
+ "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
502
+ "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
503
+ "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
504
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors",
505
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors",
506
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
507
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
508
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
509
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
510
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
511
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
512
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
513
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
514
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
515
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
516
+ "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
517
+ "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
518
+ "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
519
+ "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
520
+ "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
521
+ "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
522
+ "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
523
+ "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
524
+ "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
525
+ "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
526
+ "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
527
+ "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
528
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors",
529
+ "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors",
530
+ "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
531
+ "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
532
+ "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
533
+ "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
534
+ "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
535
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
536
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
537
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
538
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
539
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
540
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
541
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
542
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
543
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
544
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
545
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
546
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
547
+ "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors",
548
+ "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors",
549
+ "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors",
550
+ "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors",
551
+ "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors",
552
+ "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors",
553
+ "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors",
554
+ "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
555
+ "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
556
+ "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
557
+ "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
558
+ "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
559
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
560
+ "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors",
561
+ "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
562
+ "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
563
+ "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
564
+ "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
565
+ "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
566
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
567
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
568
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
569
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
570
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
571
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
572
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
573
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
574
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
575
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
576
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
577
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
578
+ "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
579
+ "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
580
+ "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
581
+ "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
582
+ "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
583
+ "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
584
+ "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
585
+ "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
586
+ "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
587
+ "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
588
+ "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
589
+ "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
590
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
591
+ "model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors",
592
+ "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
593
+ "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
594
+ "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
595
+ "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
596
+ "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
597
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
598
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
599
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
600
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
601
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
602
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors",
603
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors",
604
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors",
605
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors",
606
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors",
607
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors",
608
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors",
609
+ "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
610
+ "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
611
+ "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
612
+ "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
613
+ "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
614
+ "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
615
+ "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
616
+ "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
617
+ "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
618
+ "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
619
+ "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
620
+ "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
621
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
622
+ "model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors",
623
+ "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
624
+ "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
625
+ "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
626
+ "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
627
+ "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
628
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
629
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
630
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
631
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
632
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
633
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
634
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
635
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
636
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
637
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
638
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
639
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
640
+ "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
641
+ "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
642
+ "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
643
+ "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
644
+ "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
645
+ "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
646
+ "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
647
+ "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
648
+ "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
649
+ "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
650
+ "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00019.safetensors",
651
+ "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00019.safetensors",
652
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
653
+ "model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors",
654
+ "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
655
+ "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
656
+ "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
657
+ "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
658
+ "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
659
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors",
660
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors",
661
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors",
662
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors",
663
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors",
664
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
665
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
666
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
667
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
668
+ "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
669
+ "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
670
+ "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
671
+ "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
672
+ "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
673
+ "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
674
+ "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
675
+ "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
676
+ "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
677
+ "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
678
+ "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
679
+ "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
680
+ "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
681
+ "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
682
+ "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
683
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors",
684
+ "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors",
685
+ "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
686
+ "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
687
+ "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
688
+ "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
689
+ "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
690
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
691
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
692
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
693
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
694
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
695
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
696
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
697
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
698
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
699
+ "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
700
+ "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
701
+ "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
702
+ "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
703
+ "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
704
+ "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
705
+ "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors",
706
+ "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors",
707
+ "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors",
708
+ "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors",
709
+ "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors",
710
+ "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors",
711
+ "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors",
712
+ "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
713
+ "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
714
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
715
+ "model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors",
716
+ "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
717
+ "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
718
+ "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
719
+ "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
720
+ "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
721
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
722
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
723
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
724
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
725
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
726
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
727
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
728
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
729
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
730
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
731
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
732
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
733
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
734
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
735
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
736
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
737
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
738
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
739
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
740
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
741
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
742
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
743
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
744
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
745
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
746
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors",
747
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
748
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
749
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
750
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
751
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
752
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
753
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
754
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
755
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
756
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
757
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
758
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
759
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
760
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
761
+ "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
762
+ "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
763
+ "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
764
+ "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
765
+ "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
766
+ "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
767
+ "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
768
+ "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
769
+ "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
770
+ "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
771
+ "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
772
+ "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
773
+ "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
774
+ "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
775
+ "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
776
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
777
+ "model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors",
778
+ "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
779
+ "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
780
+ "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
781
+ "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
782
+ "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
783
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors",
784
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors",
785
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors",
786
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors",
787
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors",
788
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors",
789
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors",
790
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors",
791
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors",
792
+ "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors",
793
+ "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors",
794
+ "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors",
795
+ "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors",
796
+ "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors",
797
+ "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors",
798
+ "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
799
+ "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
800
+ "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
801
+ "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
802
+ "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
803
+ "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
804
+ "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
805
+ "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
806
+ "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
807
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors",
808
+ "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors",
809
+ "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
810
+ "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors",
811
+ "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors",
812
+ "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors",
813
+ "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors",
814
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors",
815
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors",
816
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors",
817
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors",
818
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors",
819
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors",
820
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors",
821
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
822
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
823
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
824
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
825
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
826
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
827
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
828
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
829
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
830
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
831
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
832
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
833
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
834
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
835
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
836
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
837
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
838
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
839
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors",
840
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
841
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
842
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
843
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
844
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
845
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
846
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
847
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
848
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
849
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
850
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
851
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
852
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
853
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
854
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
855
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
856
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
857
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
858
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
859
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
860
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
861
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
862
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors",
863
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors",
864
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors",
865
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors",
866
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00019.safetensors",
867
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00019.safetensors",
868
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors",
869
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
870
+ "model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors",
871
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
872
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
873
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
874
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
875
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
876
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
877
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
878
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
879
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
880
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
881
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
882
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
883
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
884
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
885
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
886
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
887
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
888
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
889
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
890
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
891
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
892
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
893
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
894
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
895
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
896
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
897
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
898
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
899
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
900
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors",
901
+ "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors",
902
+ "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
903
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
904
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
905
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
906
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
907
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
908
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
909
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
910
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
911
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
912
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
913
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
914
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
915
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
916
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
917
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors",
918
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors",
919
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors",
920
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors",
921
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors",
922
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors",
923
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors",
924
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
925
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
926
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
927
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
928
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
929
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
930
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
931
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
932
+ "model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors",
933
+ "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
934
+ "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
935
+ "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
936
+ "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
937
+ "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
938
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
939
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
940
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
941
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
942
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
943
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
944
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
945
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
946
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
947
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
948
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
949
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
950
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
951
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
952
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
953
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
954
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
955
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
956
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
957
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
958
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
959
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
960
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
961
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
962
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
963
+ "model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors",
964
+ "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
965
+ "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
966
+ "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
967
+ "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
968
+ "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
969
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
970
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
971
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
972
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors",
973
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors",
974
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors",
975
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors",
976
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors",
977
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors",
978
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors",
979
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
980
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
981
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
982
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
983
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
984
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
985
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
986
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
987
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
988
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
989
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
990
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
991
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
992
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
993
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
994
+ "model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors",
995
+ "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
996
+ "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
997
+ "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
998
+ "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
999
+ "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
1000
+ "model.norm.weight": "model-00019-of-00019.safetensors"
1001
+ }
1002
+ }
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878e73385228389512252efde0f51c65e2eb2b2610410b9b7beafc5abf2865f4
3
+ size 8567894640
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08af6f8de78b31ac60a72c02a4bdb71fffeb2d73f3203a7b9db8805e9cc94389
3
+ size 8552083416
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3876357417840060da9320795ca6d3c79f4a31a371910059984b20ea58d427
3
+ size 8566355400
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75ce60a0ffe607d4171559ace1837dedbeb8ae205e074fe517f0e0057a0274d
3
+ size 8570601080
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e9d798ce374bd2c586e6c9c9003bf0945de56169172a429c3783c3793c1708
3
+ size 926046704
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user\\'s questions.' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{% set content = 'User: ' + message['content'].strip() + '\\n' %}{% elif message['role'] == 'system' %}{% set content = message['content'].strip() + '\\n' %}{% elif message['role'] == 'assistant' %}{% set content = 'AI: ' + message['content'].strip() + '\\n' %}{% endif %}{% if loop.index0 == 0 %}{{ bos_token + system_message + '\\n' + content }}{% else %}{{ content | replace(eos_token, '') }}{% endif %}{% if loop.last and add_generation_prompt %}{{ 'AI:' }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
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
+ }