rAIfle commited on
Commit
a51fe3b
1 Parent(s): 8207f12

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ tags:
4
+ - mergekit
5
+ - merge
6
+
7
+ ---
8
+ # Sloppy-Wingman-8x7B-hf
9
+
10
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
11
+
12
+ ## Merge Details
13
+ ### Merge Method
14
+
15
+ This model was merged using the SLERP merge method.
16
+
17
+ ### Models Merged
18
+
19
+ The following models were included in the merge:
20
+ * ./02-friend2-instruct
21
+ * ./01-friend2-base
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ models:
29
+ - model: ./01-friend2-base
30
+ - model: ./02-friend2-instruct
31
+ merge_method: slerp
32
+ base_model: ./01-friend2-base
33
+ parameters:
34
+ t:
35
+ - value: 0.5
36
+ dtype: float16
37
+
38
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./01-pal-base",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.36.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: ./01-pal-base
3
+ - model: ./02-pal-instruct
4
+ merge_method: slerp
5
+ base_model: ./01-pal-base
6
+ parameters:
7
+ t:
8
+ - value: 0.5
9
+ dtype: float16
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34899b9283e77801c6fc9bbd788dce82ef85801f813644ee5bc60bdca37aee4
3
+ size 9959896976
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324d2471c1491d2312a1fc5484163230a471e77a88d0784f4bfbfd5e65e2da49
3
+ size 9915527528
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e410c63061b0474b63d138f08483175c54749a6aec8c7d7f5b4d02e85dfa2ae0
3
+ size 9966007904
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa19f1ba3dc4aa09558028310e2ae82124dcc747335ed66a1e6034bc515ee63d
3
+ size 9999479840
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25097dc04bedfec5291849d5ea9af6a4092c80a184cd1b9c1e9dd2249589344
3
+ size 9999479840
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e993a7f2a9cceb3d0917b0996dd86b1397196b5c905676e4d754b06f52d162
3
+ size 9932519576
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ce7d00cbf512daa2c3fcce555235cebfae9117c95d7145859f384fa28c2d9e
3
+ size 9915527640
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cabef2e6a70fc0327ba89c445bdd4acc8cc4ebe115f843d96a7e10501e80e5e5
3
+ size 9965942360
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c0b650f2644c99525916dc9e5a53a86132f6961f0b18011fd10d24ba6ceba3
3
+ size 9909310288
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7415e88c53a00ea16c70c138b40ea2cdac1d4863e86c41a93be560f0da69f20a
3
+ size 3842020376
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors", "lm_head.weight": "model-00009-of-00010.safetensors", "model.norm.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }