Ppoyaa commited on
Commit
6d166f4
1 Parent(s): a284646

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Ppoyaa/Lumina-5-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [Ppoyaa/Lumina-5-Instruct](https://huggingface.co/Ppoyaa/Lumina-5-Instruct)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - model: Ppoyaa/Lumina-5-Instruct
32
+ layer_range: [0, 8]
33
+ - sources:
34
+ - model: Ppoyaa/Lumina-5-Instruct
35
+ layer_range: [4, 16]
36
+ - sources:
37
+ - model: Ppoyaa/Lumina-5-Instruct
38
+ layer_range: [8, 24]
39
+ - sources:
40
+ - model: Ppoyaa/Lumina-5-Instruct
41
+ layer_range: [12, 32]
42
+ merge_method: passthrough
43
+ dtype: bfloat16
44
+
45
+
46
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Ppoyaa/Lumina-5-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": 56,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 3,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.3",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: Ppoyaa/Lumina-5-Instruct
4
+ layer_range: [0, 8]
5
+ - sources:
6
+ - model: Ppoyaa/Lumina-5-Instruct
7
+ layer_range: [4, 16]
8
+ - sources:
9
+ - model: Ppoyaa/Lumina-5-Instruct
10
+ layer_range: [8, 24]
11
+ - sources:
12
+ - model: Ppoyaa/Lumina-5-Instruct
13
+ layer_range: [12, 32]
14
+ merge_method: passthrough
15
+ dtype: bfloat16
16
+
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e7a6b7a311c9f757522164faa467ac2cde2f5c3d971b583e263a0239e0763b
3
+ size 9920013008
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0ea92443c688d83004696d622928d32ca7ea2f08e8b9ebae5ed4ef3683e0f2
3
+ size 9982454760
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db774b0954fa958fd91d068c8b596593c51117d08a707afd8b59ef885184c644
3
+ size 9982454728
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0ebdada27fc2f31f8de72dfa3fa9fb1435d7c45a8e2dcd73b1166ae8feb2b7
3
+ size 9982454760
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8db40bf26cc29bc6867943b5f27cf14c89600b7dec7e904ab13b70ea5a38d5d
3
+ size 9982454728
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc7a400af607cde66837eceb873b69c67fda50ac77fbf7d334dd9420670edcc
3
+ size 9999265920
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07a54aecfd2a1d5a7f4e01cdfd89ffbf7100e75be81c445e7f96fde3844b417
3
+ size 4565243408
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 64414228480}, "weight_map": {"lm_head.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": null,
36
+ "model_max_length": 32768,
37
+ "pad_to_multiple_of": null,
38
+ "pad_token": "<s>",
39
+ "pad_token_type_id": 0,
40
+ "padding_side": "left",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }