Upload folder using huggingface_hub
Browse files- config.json +34 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "jondurbin/nontoxic-bagel-34b-v0.2",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 200000,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 60,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"num_local_experts": 2,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 5000000.0,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"sliding_window": null,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.36.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 64000
|
34 |
+
}
|
model-00001-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faf3d3fc423827a3bf8fd8b4769862adbbb0843a4a75fe149614af0e075e4093
|
3 |
+
size 9763127632
|
model-00002-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e36788c06e4060fd9ea5524905de0a5024be62dba774b792731b3ce53562577
|
3 |
+
size 9982448040
|
model-00003-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81259cafdfd38c5cac7aca1ef44c384196db0744966b4a0ba95dffe48a31f592
|
3 |
+
size 9982448040
|
model-00004-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebe3109ff151e56a26c528b844d2700b18b41f2432cd9ecbcd4ddd6d85630d15
|
3 |
+
size 9982448024
|
model-00005-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8e9e384c92bc7c2509fba33111b0d57ac56b875d9fd8b9a04f584e53515dafb
|
3 |
+
size 9982448024
|
model-00006-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6baf3e781a4bf69201aaf327ce73905b010ace0aae6a8ccb8f771b991ec64a9b
|
3 |
+
size 9982448040
|
model-00007-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b5b8702945e376ddf13d4024bfe887f4b3a67750eb1254af55350515d53eac3
|
3 |
+
size 9982448040
|
model-00008-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3033684e7f9cda80e9fd820723cf3c2c8d17fcaa1edfb5e38726150eeb37b253
|
3 |
+
size 9982448016
|
model-00009-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbc5e3396bdfd215a40eb6cc4d053bb33a7c0f1b349bba8b02ee783398503684
|
3 |
+
size 9982448040
|
model-00010-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fef46eb573db39e4fb5b964df56e7a92965d93741c1276970b1eec81843ecafd
|
3 |
+
size 9982448040
|
model-00011-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9b83ef7b5782a2066ad11bf01408ec64e7d1b1b3d5bb7e8e6eee8f561387f50
|
3 |
+
size 9983316832
|
model-00012-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b932afa6ad3721accf045e1f1e24037ecd78005bf4abc7a29fdc41211a8ed137
|
3 |
+
size 9982467080
|
model-00013-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fccb002bfa06f2f76840d0924733614973eccca63ce4785d6db0a67e42942303
|
3 |
+
size 2056938536
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 200000,
|
36 |
+
"pad_token": "<s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|