Upload 26 files
Browse files- config.json +31 -0
- mergekit_config.yml +7 -0
- model-00001-of-00019.safetensors +3 -0
- model-00002-of-00019.safetensors +3 -0
- model-00003-of-00019.safetensors +3 -0
- model-00004-of-00019.safetensors +3 -0
- model-00005-of-00019.safetensors +3 -0
- model-00006-of-00019.safetensors +3 -0
- model-00007-of-00019.safetensors +3 -0
- model-00008-of-00019.safetensors +3 -0
- model-00009-of-00019.safetensors +3 -0
- model-00010-of-00019.safetensors +3 -0
- model-00011-of-00019.safetensors +3 -0
- model-00012-of-00019.safetensors +3 -0
- model-00013-of-00019.safetensors +3 -0
- model-00014-of-00019.safetensors +3 -0
- model-00015-of-00019.safetensors +3 -0
- model-00016-of-00019.safetensors +3 -0
- model-00017-of-00019.safetensors +3 -0
- model-00018-of-00019.safetensors +3 -0
- model-00019-of-00019.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models/Mixtral-8x7B-v0.1-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.02,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: models/migtissera_Tess-2.0-Mixtral-8x7B-v0.2
|
3 |
+
- model: models/Sao10K_Typhon-Mixtral-v1
|
4 |
+
- model: models/rombodawg_Open_Gpt4_8x7B_v0.2
|
5 |
+
merge_method: model_stock
|
6 |
+
base_model: models/Mixtral-8x7B-v0.1-Instruct
|
7 |
+
dtype: float16
|
model-00001-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10c217d8ff99e16cf48afd0cb23bf24eb07a247b770adb97dd8c3a3372f8be41
|
3 |
+
size 4953560784
|
model-00002-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57eb59fdaacb489720b2b00dcac9b78a1292e05feda5b3f1af93ea7122ddc37b
|
3 |
+
size 4983004000
|
model-00003-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a54f34f35aa9950e9fb26883090b1e71deaee65c81dd293f79bf9bf68a31c76
|
3 |
+
size 4899035200
|
model-00004-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:310f039b8008324ae3faa48735f912058a6d0ebfe30839dc1a7fd6cf6135d713
|
3 |
+
size 4983004008
|
model-00005-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037b4f011e1de699bd7ad8d3b5cf6bb25f7a7eac67d037de2aca8a7c29b9fc7a
|
3 |
+
size 4983004008
|
model-00006-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1b9bc1c94b34a2a18771a4d2a55a551a2a6e7c3c981845f2ec3899785d14abc
|
3 |
+
size 4983004016
|
model-00007-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:780e1f34b78e06ad040b7aff7a83c62d882a06da428ef8a597d79405c46f8e14
|
3 |
+
size 4899035200
|
model-00008-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b1a2616d88c376d20bca5a23e3182c0d0ab8de13631b06900cbe745838baff
|
3 |
+
size 4983003976
|
model-00009-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80d2ecbcae9f8276d12d9b9b3145b51361fc1b67f7e902d2f5dbd5c69d7a3741
|
3 |
+
size 4983004016
|
model-00010-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e21bbd81a6c068d13ee2ea3b4fb51af5fced9ad952e353be3a677fe053af7f6
|
3 |
+
size 4899035200
|
model-00011-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43bfc843a6386ccd5b84a838a4aa8aee96c7de5e2cb33a9ee2ca7fad0347d758
|
3 |
+
size 4983004008
|
model-00012-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb90ceec716ea3a0f0f377b75da8e700cbbb19c9b017ffd71b6399bedb3d86dc
|
3 |
+
size 4983004016
|
model-00013-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01f47b479c5d3615e94b6b35e7cdc617964558d8e2021992aa20ef19b9450584
|
3 |
+
size 4983004016
|
model-00014-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:855e92f96302a5000e494370d4e4ac13214a14150c8ad1b29d4025939ba0dd73
|
3 |
+
size 4899035184
|
model-00015-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d23fe3ee42ef03cf42c08fdf34787d94659baf704f66b0492320212a1795af66
|
3 |
+
size 4983003992
|
model-00016-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96d879b9f96aa169b200f2f8a15a143a36f8b04425b7af7311d9781c428ee4d5
|
3 |
+
size 4983003984
|
model-00017-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e034ce12d91242bdf6b1fff4d4bd94ffa851903f3d75b7b182873fe717ec4919
|
3 |
+
size 4899035152
|
model-00018-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84b17449a632ae92a0ea6bfffbc5f654badcda8420eacc951a4762f433e95586
|
3 |
+
size 4983003952
|
model-00019-of-00019.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:888c99bc1890f2f62740f90d5510f140927d899204bf806ffc115d93d70f38f8
|
3 |
+
size 4160927752
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 93405585408}, "weight_map": {"lm_head.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false,
|
42 |
+
"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 %}"
|
43 |
+
}
|