sandmanbuzz commited on
Commit
115e05d
1 Parent(s): 086ce14

We kinda don't have an fp16 of this anywhere do we?

Browse files
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # Air-Striker-Mixtral-8x7B-ZLoss-Instruct
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
22
+ * ./Air-Striker-Mixtral-8x7B-ZLoss-noninstruct/merged
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ models:
30
+ - model: mistralai/Mixtral-8x7B-Instruct-v0.1
31
+ parameters:
32
+ weight: 0.5
33
+ - model: ./Air-Striker-Mixtral-8x7B-ZLoss-noninstruct/merged
34
+ parameters:
35
+ weight: 0.5
36
+ merge_method: linear
37
+ dtype: bfloat16
38
+
39
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
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": "bfloat16",
27
+ "transformers_version": "4.38.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: mistralai/Mixtral-8x7B-Instruct-v0.1
3
+ parameters:
4
+ weight: 0.5
5
+ - model: ./Air-Striker-Mixtral-8x7B-ZLoss-noninstruct/merged
6
+ parameters:
7
+ weight: 0.5
8
+ merge_method: linear
9
+ dtype: bfloat16
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f231094f20febe0afd3fa068e7aec31b067d99315042dc2ef59c8d5ad6ded2
3
+ size 9959831440
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88bb9eae64681c780c1e2e6646a1d61a735aa97be516e553419ae7fdc9ffff0
3
+ size 9915527640
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a16f9604527e2f6519842c1d0223bc09d40be5b79544611fbdcdec3db2148cd
3
+ size 9966008016
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14e5ec4b58a9d8c854e907fbcaf11b38a02a939db5bc041d9a2622683be3a00
3
+ size 9999479944
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd5732634befda0a15c6e579935e5d65f8d6bcdaf060b275116f0727437118b
3
+ size 9999479944
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14698edfa6b1e2b4f45b27871fb73803f2b7cad9ce8ccf0e9d25e4ef0f19c2bd
3
+ size 9932519688
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c870ecdcbcccce4e8e60aab981b51acefe9eed4cee94f17304c6f19a2b83a2
3
+ size 9915527736
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1f904f46f4d2c415303daef61467e13b986972b47729367039188fb2aba59c
3
+ size 9966008120
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4584ff392587bd469e2636c4826ab5cbc8b59029bcb479f2ea903617744716
3
+ size 9909310392
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9b0884407b83f84f03e77b90a2004162d51f34c0bece6d4c57c032c4dbd82d
3
+ size 3842020416
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.1.block_sparse_moe.gate.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.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.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.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.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "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.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.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.8.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-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.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.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.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00003-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.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.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.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-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.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.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.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.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-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.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.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.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.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-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.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.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.25.block_sparse_moe.gate.weight": "model-00007-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.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.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", "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.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-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.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.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.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.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-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.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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }