rhplus0831 commited on
Commit
0af101c
1 Parent(s): c49c22f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ycros/BagelMIsteryTour-v2-8x7B
4
+ - NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
5
+ - smelborp/MixtralOrochi8x7B
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # maid-yuzu-v3
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [smelborp/MixtralOrochi8x7B](https://huggingface.co/smelborp/MixtralOrochi8x7B) as a base.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [ycros/BagelMIsteryTour-v2-8x7B](https://huggingface.co/ycros/BagelMIsteryTour-v2-8x7B)
24
+ * [NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ base_model:
32
+ model:
33
+ path: smelborp/MixtralOrochi8x7B
34
+ dtype: bfloat16
35
+ merge_method: dare_ties
36
+ slices:
37
+ - sources:
38
+ - layer_range: [0, 32]
39
+ model:
40
+ model:
41
+ path: ycros/BagelMIsteryTour-v2-8x7B
42
+ parameters:
43
+ density: 0.6
44
+ weight: 0.25
45
+ - layer_range: [0, 32]
46
+ model:
47
+ model:
48
+ path: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
49
+ parameters:
50
+ density: 0.4
51
+ weight: 0.1
52
+ - layer_range: [0, 32]
53
+ model:
54
+ model:
55
+ path: smelborp/MixtralOrochi8x7B
56
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "smelborp/MixtralOrochi8x7B",
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": "4.37.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model:
2
+ model:
3
+ path: smelborp/MixtralOrochi8x7B
4
+ dtype: bfloat16
5
+ merge_method: dare_ties
6
+ slices:
7
+ - sources:
8
+ - layer_range: [0, 32]
9
+ model:
10
+ model:
11
+ path: ycros/BagelMIsteryTour-v2-8x7B
12
+ parameters:
13
+ density: 0.6
14
+ weight: 0.25
15
+ - layer_range: [0, 32]
16
+ model:
17
+ model:
18
+ path: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
19
+ parameters:
20
+ density: 0.4
21
+ weight: 0.1
22
+ - layer_range: [0, 32]
23
+ model:
24
+ model:
25
+ path: smelborp/MixtralOrochi8x7B
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474695b4eb1c1058b9c62a38843fbc8897b876260f11b0d7a8fe55336003d63f
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:fdc580d0682618042330d0d369949a81b523f2a03730aeb08003b7adf5a6f6c1
3
+ size 9915527640
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2886b2fe4087e3b1049fbf9b05a1c12b03e6e71677bf989a4dfff82590f58dca
3
+ size 9966008016
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5395e6c0ae1d578be632d1c38b3bc0ffc4d9336cca22e257dc8c5a1d3434bd39
3
+ size 9999479944
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9998b1364bb5eb002c44915a3a09dbb8a66fa067e84be9c09055a94b69c7666a
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:d898e34336a8c0b405889a5f51171d277e579926227fa6c23c3e3e6ef2a0048d
3
+ size 9932519688
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed186cc8beb1c95e6ed38da2baf32fdc88a6102c7eaa39c07305cb5fdd2d236
3
+ size 9915527736
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094fdc26e8b7ff7eb9110c78f15de76fba6e2d8ab5112e5a637b03d8d6d9d572
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:b126283d00c4740fcbab799a2bbb24a5d80c05291ae4e663c6dcd6d6350c3860
3
+ size 9909310392
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017c3b63fb81280d4c6126dea80d13f8a97f3ba3c1336cef77e32ea6320585b1
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }