allknowingroger
commited on
Commit
•
16a9567
1
Parent(s):
6f93f1b
Upload folder using huggingface_hub
Browse files- README.md +55 -0
- config.json +30 -0
- mergekit_moe_config.yml +7 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.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 +43 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- frankenmoe
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- allknowingroger/MultiMerge-7B-slerp
|
10 |
+
- allknowingroger/Calmex26-7B-slerp
|
11 |
+
base_model:
|
12 |
+
- allknowingroger/MultiMerge-7B-slerp
|
13 |
+
- allknowingroger/Calmex26-7B-slerp
|
14 |
+
---
|
15 |
+
|
16 |
+
# Calmex26merge-12B-MoE
|
17 |
+
|
18 |
+
Calmex26merge-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
19 |
+
* [allknowingroger/MultiMerge-7B-slerp](https://huggingface.co/allknowingroger/MultiMerge-7B-slerp)
|
20 |
+
* [allknowingroger/Calmex26-7B-slerp](https://huggingface.co/allknowingroger/Calmex26-7B-slerp)
|
21 |
+
|
22 |
+
## 🧩 Configuration
|
23 |
+
|
24 |
+
```yaml
|
25 |
+
base_model: allknowingroger/MultiMerge-7B-slerp
|
26 |
+
experts:
|
27 |
+
- source_model: allknowingroger/MultiMerge-7B-slerp
|
28 |
+
positive_prompts: ["what"]
|
29 |
+
- source_model: allknowingroger/Calmex26-7B-slerp
|
30 |
+
positive_prompts: ["why"]
|
31 |
+
```
|
32 |
+
|
33 |
+
## 💻 Usage
|
34 |
+
|
35 |
+
```python
|
36 |
+
!pip install -qU transformers bitsandbytes accelerate
|
37 |
+
|
38 |
+
from transformers import AutoTokenizer
|
39 |
+
import transformers
|
40 |
+
import torch
|
41 |
+
|
42 |
+
model = "allknowingroger/Calmex26merge-12B-MoE"
|
43 |
+
|
44 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
45 |
+
pipeline = transformers.pipeline(
|
46 |
+
"text-generation",
|
47 |
+
model=model,
|
48 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
49 |
+
)
|
50 |
+
|
51 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
52 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
53 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
54 |
+
print(outputs[0]["generated_text"])
|
55 |
+
```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allknowingroger/MultiMerge-7B-slerp",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 2,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.39.3",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: allknowingroger/MultiMerge-7B-slerp
|
3 |
+
experts:
|
4 |
+
- source_model: allknowingroger/MultiMerge-7B-slerp
|
5 |
+
positive_prompts: ["what"]
|
6 |
+
- source_model: allknowingroger/Calmex26-7B-slerp
|
7 |
+
positive_prompts: ["why"]
|
model-00001-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eb5cb46f58d8fbe9dff219b05e9950488cfdf68db52440580172275cda08bf7
|
3 |
+
size 1933849912
|
model-00002-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14c6cea15277d2dee481f9ece48798386da9b9d728a70d5d8a80d7027288a401
|
3 |
+
size 1996490960
|
model-00003-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f57e8a908b822bf875b613b1eb3ad03589224b2f726e7a223ec97fd4c23eb586
|
3 |
+
size 1996490968
|
model-00004-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d60c9e18c55b47a8befcf436858ad14e8c25d4d6808dadf029b62f029ab1e33
|
3 |
+
size 1996490968
|
model-00005-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b6a46e4d69fb8f9a3907648401f4c3da594e989a00aaa1df69b08ae012e19a4
|
3 |
+
size 1996490952
|
model-00006-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e62f21bbaa004c4f5c4a5935108d57151b4fae63e7b4aeb5f029e23f1e01283
|
3 |
+
size 1996490960
|
model-00007-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709db9de9d696ca2af214f5209c28a509dcc02854d042b9cb391d3d2b2e7834f
|
3 |
+
size 1996490968
|
model-00008-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:596e9b696a9c8de48e867401564e0b7c0bc6f26b301e806fa2a6d794143a391c
|
3 |
+
size 1996490960
|
model-00009-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2400c0fe1c24428b8a7e19381f2c4334ea4c9477a076c0b3fc71749cd7df96ce
|
3 |
+
size 1996490952
|
model-00010-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28adf2668a02c04ed485c91da6a6d59b820bdd0daa6b2a5c8789020f7c297c9a
|
3 |
+
size 1996490968
|
model-00011-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d42beb339d4d54d0dc8bcbb67ce5c0969c7a5def03fd033ab2f108c6e9e678c2
|
3 |
+
size 1996490968
|
model-00012-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3c0addb98701d4d73131a90d9e3c9b714b35cda71a9ae5bacdeabac9716e73f
|
3 |
+
size 1979981568
|
model-00013-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b40939d871ad915e99690c41caff3e2d890ce2d91675d5dfb77d96e1f79137c
|
3 |
+
size 1879588416
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 32768,
|
36 |
+
"pad_token": "<s>",
|
37 |
+
"padding_side": "left",
|
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 |
+
}
|