Upload folder using huggingface_hub
Browse files- README.md +73 -0
- config.json +30 -0
- model-00001-of-00010.safetensors +3 -0
- model-00002-of-00010.safetensors +3 -0
- model-00003-of-00010.safetensors +3 -0
- model-00004-of-00010.safetensors +3 -0
- model-00005-of-00010.safetensors +3 -0
- model-00006-of-00010.safetensors +3 -0
- model-00007-of-00010.safetensors +3 -0
- model-00008-of-00010.safetensors +3 -0
- model-00009-of-00010.safetensors +3 -0
- model-00010-of-00010.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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
|
5 |
+
- en
|
6 |
+
---
|
7 |
+
<!-- header start -->
|
8 |
+
<!-- 200823 -->
|
9 |
+
|
10 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
11 |
+
<img src="https://github.com/janhq/jan/assets/89722390/35daac7d-b895-487c-a6ac-6663daaad78e" alt="Jan banner" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
12 |
+
</div>
|
13 |
+
|
14 |
+
<p align="center">
|
15 |
+
<a href="https://jan.ai/">Jan</a>
|
16 |
+
- <a href="https://discord.gg/AsJ8krTT3N">Discord</a>
|
17 |
+
</p>
|
18 |
+
<!-- header end -->
|
19 |
+
|
20 |
+
# Model Description
|
21 |
+
This is a highly experimental model for merging models into a MOE model.
|
22 |
+
- base model: [trinity-v1](https://huggingface.co/janhq/trinity-v1)
|
23 |
+
1. [trinity-v1](https://huggingface.co/janhq/trinity-v1): for General Chat
|
24 |
+
2. [Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B): for Role-playing
|
25 |
+
3. [CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf): for Coding
|
26 |
+
4. [Seraph-7B](https://huggingface.co/Weyaxi/Seraph-7B): for Writing
|
27 |
+
|
28 |
+
Special thanks to the interested work of [Chargoddard](https://huggingface.co/chargoddard) and [Undi95](https://huggingface.co/Undi95)
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
Updating
|
32 |
+
```
|
33 |
+
|
34 |
+
# Run this model
|
35 |
+
You can run this model using [Jan Desktop](https://jan.ai/) on Mac, Windows, or Linux.
|
36 |
+
|
37 |
+
Jan is an open source, ChatGPT alternative that is:
|
38 |
+
|
39 |
+
- 💻 **100% offline on your machine**
|
40 |
+
: Your conversations remain confidential, and visible only to you.
|
41 |
+
- 🗂️ **An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.
|
42 |
+
- 🌐 **OpenAI Compatible**: Local server on port `1337` with OpenAI compatible endpoints
|
43 |
+
- 🌍 **Open Source & Free**: We build in public; check out our [Github](https://github.com/janhq)
|
44 |
+
|
45 |
+

|
46 |
+
|
47 |
+
# About Jan
|
48 |
+
Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.
|
49 |
+
|
50 |
+
Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.
|
51 |
+
|
52 |
+
# Jan Model Merger
|
53 |
+
This is a test project for merging models.
|
54 |
+
|
55 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
56 |
+
|
57 |
+
Detailed results can be found here.
|
58 |
+
|
59 |
+
| Metric | Value |
|
60 |
+
|-----------------------|---------------------------|
|
61 |
+
| Avg. | ?|
|
62 |
+
| ARC (25-shot) | ? |
|
63 |
+
| HellaSwag (10-shot) | ? |
|
64 |
+
| MMLU (5-shot) | ?|
|
65 |
+
| TruthfulQA (0-shot) | ? |
|
66 |
+
| Winogrande (5-shot) | ? |
|
67 |
+
| GSM8K (5-shot) | ? |
|
68 |
+
|
69 |
+
# Acknowlegement
|
70 |
+
- [mergekit]
|
71 |
+
(https://github.com/cg123/mergekit)
|
72 |
+
- [DARE](https://github.com/yule-BUAA/MergeLM/blob/main/README.md)
|
73 |
+
- [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness)
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"sliding_window": 32768,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.36.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
model-00001-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d068a81b1fb3d8a5cf5910cd99658b33f0fee706a1cf28c0a106a00ca7742f5c
|
3 |
+
size 9919813632
|
model-00002-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65253baa3e423d5d087eeb84a462e18a17e4eb9d85e3fbc48b3a311f0febcba8
|
3 |
+
size 9982454728
|
model-00003-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96ea946deca5c672ecef4a8a91836cad6682a30d99dfc012083fa4fa9993e349
|
3 |
+
size 9982454728
|
model-00004-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b98374edd8db0219005454f03e74fb314e03bd55e33c899d91b270e0f381dd0
|
3 |
+
size 9982454648
|
model-00005-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11f343f17fd149235d4fc54d69b382a89a868727fbc19e9a2b31618c3c972d4a
|
3 |
+
size 9982454728
|
model-00006-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1046b7b869c3ce15441c4adcc1db572a301f1b49fb8050cde05e28d2782c74
|
3 |
+
size 9982454728
|
model-00007-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff9ba576c94ca54b314e4c84abad9d752340e07ddbb97bbeaabcae471db7c99f
|
3 |
+
size 9982454648
|
model-00008-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beddd9ad0d00a8c9f3e853e858b287d2b91873ec3625f705a4d2ad41f9b78c45
|
3 |
+
size 9982454728
|
model-00009-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0279ab830212dbc1414e8b601e53db80bea8cfc9ecac3af5423c49d94d09e59
|
3 |
+
size 9982454728
|
model-00010-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:265d280aa0fcb1a4ae1891c7bf55a09179b55eea5c5f267966801e604eeb0f18
|
3 |
+
size 3626261624
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.norm.weight": "model-00001-of-00010.safetensors", "lm_head.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "<s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|