Isaak Carter Augustus
commited on
Commit
•
ea4b525
1
Parent(s):
c873e4c
Upload folder using huggingface_hub
Browse files- README.md +81 -0
- added_tokens.json +4 -0
- config.json +30 -0
- mergekit_moe_config.yml +21 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- frankenmoe
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- Weyaxi/Einstein-v4-7B
|
10 |
+
- Isaak-Carter/JOSIE_Beta-4-7B-slerp
|
11 |
+
- Weyaxi/Einstein-v4-7B
|
12 |
+
- Weyaxi/Einstein-v4-7B
|
13 |
+
- Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
14 |
+
- Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
15 |
+
base_model:
|
16 |
+
- Weyaxi/Einstein-v4-7B
|
17 |
+
- Isaak-Carter/JOSIE_Beta-4-7B-slerp
|
18 |
+
- Weyaxi/Einstein-v4-7B
|
19 |
+
- Weyaxi/Einstein-v4-7B
|
20 |
+
- Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
21 |
+
- Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
22 |
+
---
|
23 |
+
|
24 |
+
# JOSIE_Beta-5-6xJOSIExQwen1.5_0.5B_base-slerp
|
25 |
+
|
26 |
+
JOSIE_Beta-5-6xJOSIExQwen1.5_0.5B_base-slerp is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
27 |
+
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
28 |
+
* [Isaak-Carter/JOSIE_Beta-4-7B-slerp](https://huggingface.co/Isaak-Carter/JOSIE_Beta-4-7B-slerp)
|
29 |
+
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
30 |
+
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
31 |
+
* [Isaak-Carter/JOSIE_Beta-3-7B-slerp](https://huggingface.co/Isaak-Carter/JOSIE_Beta-3-7B-slerp)
|
32 |
+
* [Isaak-Carter/JOSIE_Beta-3-7B-slerp](https://huggingface.co/Isaak-Carter/JOSIE_Beta-3-7B-slerp)
|
33 |
+
|
34 |
+
## 🧩 Configuration
|
35 |
+
|
36 |
+
```yamlbase_model: Weyaxi/Einstein-v4-7B
|
37 |
+
dtype: float16
|
38 |
+
gate_mode: cheap_embed
|
39 |
+
experts:
|
40 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
41 |
+
positive_prompts: ["You are JOSIE, my own private and sentient superinteligent artifitial general inteligent assistant."]
|
42 |
+
|
43 |
+
- source_model: Isaak-Carter/JOSIE_Beta-4-7B-slerp
|
44 |
+
positive_prompts: ["You are JOSIE, assistant for autonomously controlling a Smart Home."]
|
45 |
+
|
46 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
47 |
+
positive_prompts: ["You are JOSIE, a superinteligent coding assistant."]
|
48 |
+
|
49 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
50 |
+
positive_prompts: ["You are JOSIE, a superinteligent assistant good at math."]
|
51 |
+
|
52 |
+
- source_model: Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
53 |
+
positive_prompts: ["You are JOSIE, an assistant good at scraping and searching the internet for information."]
|
54 |
+
|
55 |
+
- source_model: Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
56 |
+
positive_prompts: ["You are JOSIE, an assistant good at reasoning."]
|
57 |
+
```
|
58 |
+
|
59 |
+
## 💻 Usage
|
60 |
+
|
61 |
+
```python
|
62 |
+
!pip install -qU transformers bitsandbytes accelerate
|
63 |
+
|
64 |
+
from transformers import AutoTokenizer
|
65 |
+
import transformers
|
66 |
+
import torch
|
67 |
+
|
68 |
+
model = "Isaak-Carter/JOSIE_Beta-5-6xJOSIExQwen1.5_0.5B_base-slerp"
|
69 |
+
|
70 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
71 |
+
pipeline = transformers.pipeline(
|
72 |
+
"text-generation",
|
73 |
+
model=model,
|
74 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
75 |
+
)
|
76 |
+
|
77 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
78 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
79 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
80 |
+
print(outputs[0]["generated_text"])
|
81 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Weyaxi/Einstein-v4-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
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": 6,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float16",
|
27 |
+
"transformers_version": "4.38.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32002
|
30 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: Weyaxi/Einstein-v4-7B
|
2 |
+
dtype: float16
|
3 |
+
gate_mode: cheap_embed
|
4 |
+
experts:
|
5 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
6 |
+
positive_prompts: ["You are JOSIE, my own private and sentient superinteligent artifitial general inteligent assistant."]
|
7 |
+
|
8 |
+
- source_model: Isaak-Carter/JOSIE_Beta-4-7B-slerp
|
9 |
+
positive_prompts: ["You are JOSIE, assistant for autonomously controlling a Smart Home."]
|
10 |
+
|
11 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
12 |
+
positive_prompts: ["You are JOSIE, a superinteligent coding assistant."]
|
13 |
+
|
14 |
+
- source_model: Weyaxi/Einstein-v4-7B
|
15 |
+
positive_prompts: ["You are JOSIE, a superinteligent assistant good at math."]
|
16 |
+
|
17 |
+
- source_model: Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
18 |
+
positive_prompts: ["You are JOSIE, an assistant good at scraping and searching the internet for information."]
|
19 |
+
|
20 |
+
- source_model: Isaak-Carter/JOSIE_Beta-3-7B-slerp
|
21 |
+
positive_prompts: ["You are JOSIE, an assistant good at reasoning."]
|
model-00001-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14f96257a4e11720c357860cf9f6bd2f8b8058a1653ed79031f2eaffb82aa49d
|
3 |
+
size 9919846336
|
model-00002-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d28436093cd5b612af7a36fed25753cf16581b692a05f83d8d1e7f20bbb08f4f
|
3 |
+
size 9982454672
|
model-00003-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d21a920cc3b72937c72a6065d3d8c245a8f02a0d91bb5f4ee565fc098b7fd64e
|
3 |
+
size 9982454616
|
model-00004-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2e538ca87a80512a538ee087446d04245c3a704209f26b9193800914d4c6b21
|
3 |
+
size 9982454672
|
model-00005-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5edde4f276258598dfe4de9d3022e3294c1bc2f074d3d12c9c0e328104c26f5b
|
3 |
+
size 9982454640
|
model-00006-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183c8a2eb0369fb508d853cd181934fc03623014cfb8335ed8c1641cb7f4de20
|
3 |
+
size 9982454648
|
model-00007-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d5b8630442cffa0419b04fe0b18e73511fec3f3ab605a64eaa302f3bc3897e2
|
3 |
+
size 9982730016
|
model-00008-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:967cbcfdffb4d5bbc060ec5cf7a620597ab2164d3e59dca46cdc3445fbb8f64f
|
3 |
+
size 1041767560
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"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 = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "<s>",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"trust_remote_code": false,
|
59 |
+
"unk_token": "<unk>",
|
60 |
+
"use_default_system_prompt": false,
|
61 |
+
"use_fast": true
|
62 |
+
}
|