blockblockblock
commited on
Commit
•
191c428
1
Parent(s):
199114d
Upload folder using huggingface_hub
Browse files- README.md +41 -0
- added_tokens.json +3 -0
- config.json +45 -0
- model.safetensors.index.json +1 -0
- output-00001-of-00003.safetensors +3 -0
- output-00002-of-00003.safetensors +3 -0
- output-00003-of-00003.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +51 -0
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
tags:
|
4 |
+
- not-for-all-audiences
|
5 |
+
- nsfw
|
6 |
+
- merge
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- description start -->
|
10 |
+
## Description
|
11 |
+
|
12 |
+
This repo contains fp16 files of LewdGem-40B, a MoE model of the 4 best llama2 model of Undi95 and NeverSleep repo.
|
13 |
+
|
14 |
+
Since I don't have a lot of time or ressource to train new model at the moment, I didn't wanted to let my repo dry, so I got the idea to make a MoE of my most liked/used ERP model (and the last Noromaid supporting Alpaca).
|
15 |
+
|
16 |
+
I moved out correctly and I'm comfy in my new home, thank you all for the support!
|
17 |
+
|
18 |
+
<!-- description end -->
|
19 |
+
<!-- description start -->
|
20 |
+
## Models used
|
21 |
+
|
22 |
+
- [NeverSleep/Noromaid-13b-v0.3](https://huggingface.co/NeverSleep/Noromaid-13b-v0.3)
|
23 |
+
- [Undi95/Xwin-MLewd-13B-V0.2](https://huggingface.co/Undi95/Xwin-MLewd-13B-V0.2)
|
24 |
+
- [Undi95/Emerhyst-13B](https://huggingface.co/Undi95/Emerhyst-13B)
|
25 |
+
- [Undi95/MLewdBoros-L2-13B](https://huggingface.co/Undi95/MLewdBoros-L2-13B)
|
26 |
+
|
27 |
+
## Prompt template: Alpaca
|
28 |
+
|
29 |
+
```
|
30 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
31 |
+
|
32 |
+
### Instruction:
|
33 |
+
{system prompt}
|
34 |
+
|
35 |
+
### Input:
|
36 |
+
{prompt}
|
37 |
+
|
38 |
+
### Response:
|
39 |
+
```
|
40 |
+
|
41 |
+
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Undi95/LewdGem",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 13824,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 40,
|
19 |
+
"num_key_value_heads": 40,
|
20 |
+
"num_local_experts": 4,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 10000.0,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"sliding_window": null,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float16",
|
31 |
+
"transformers_version": "4.39.0.dev0",
|
32 |
+
"use_cache": false,
|
33 |
+
"vocab_size": 32000,
|
34 |
+
"quantization_config": {
|
35 |
+
"quant_method": "exl2",
|
36 |
+
"version": "0.0.15",
|
37 |
+
"bits": 4.0,
|
38 |
+
"head_bits": 6,
|
39 |
+
"calibration": {
|
40 |
+
"rows": 100,
|
41 |
+
"length": 2048,
|
42 |
+
"dataset": "(default)"
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}
|
output-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31dfc2bcd5d83fc1a5b360cd3f109b99da1fa47704cbc9fcb2f0e22ce7067a42
|
3 |
+
size 8573602712
|
output-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a1767ec13bdab249491be0f60b193c46e566f9f25664268836a11b5c19fbde
|
3 |
+
size 8568696744
|
output-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad3a59b917e6d151c41c3c8188a6da35e87dcf711cb52ae12399a6a5d5e46a71
|
3 |
+
size 2398993056
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[PAD]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": true,
|
42 |
+
"model_max_length": 2048,
|
43 |
+
"pad_token": "<s>",
|
44 |
+
"padding_side": "left",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"tokenizer_class": "LlamaTokenizer",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": false,
|
50 |
+
"use_fast": true
|
51 |
+
}
|