allknowingroger commited on
Commit
45464f2
1 Parent(s): 1ff1c39

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
7
+ - allknowingroger/Calmex26merge-12B-MoE
8
+ base_model:
9
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
10
+ - allknowingroger/Calmex26merge-12B-MoE
11
+ ---
12
+
13
+ # MultiMash9-13B-slerp
14
+
15
+ MultiMash9-13B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
17
+ * [allknowingroger/Calmex26merge-12B-MoE](https://huggingface.co/allknowingroger/Calmex26merge-12B-MoE)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
25
+ layer_range: [0, 32]
26
+ - model: allknowingroger/Calmex26merge-12B-MoE
27
+ layer_range: [0, 32]
28
+ merge_method: slerp
29
+ base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
30
+ parameters:
31
+ t:
32
+ - filter: self_attn
33
+ value: [0, 0.5, 0.3, 0.7, 1]
34
+ - filter: mlp
35
+ value: [1, 0.5, 0.7, 0.3, 0]
36
+ - value: 0.5
37
+ dtype: bfloat16
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "allknowingroger/MultiMash9-13B-slerp"
50
+ messages = [{"role": "user", "content": "What is a large language model?"}]
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained(model)
53
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
+ pipeline = transformers.pipeline(
55
+ "text-generation",
56
+ model=model,
57
+ torch_dtype=torch.float16,
58
+ device_map="auto",
59
+ )
60
+
61
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
+ print(outputs[0]["generated_text"])
63
+ ```
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 2,
20
+ "output_router_logits": false,
21
+ "pad_token_id": 2,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 10000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.41.0",
30
+ "unsloth_version": "2024.1",
31
+ "use_cache": false,
32
+ "vocab_size": 32000
33
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
5
+ layer_range: [0, 32]
6
+ - model: allknowingroger/Calmex26merge-12B-MoE
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: bfloat16
model-00001-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714a9a1b61e7c921381e3f6a6baf6a72c7c9d0520d73fad0e0b23c81fcb8f898
3
+ size 994050792
model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1f217ef977a6c5fc8b64871fef385a698e627d6609ed819213c41fa6f92900
3
+ size 906004176
model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d046c43524cf700bbfb850ab090b23bddcb95fe32643d4064817fe02d8cc6a3b
3
+ size 989923840
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeaf8531945707c17302f58a4da908fc2f208ca5368127230499876659d41268
3
+ size 906004192
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fa54e03adfedefad50c080ae3cd2e73085055d5eed4c4845f48b1d5f14b204
3
+ size 906004192
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64582549269593bd37dee9297a56fcd49a8ac1fb0fe2c509df520e0cede15f5
3
+ size 906004192
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:227e443c9ffa4ee7e7a689cf28016fb5662ba3af473705a93e19be4edbeda488
3
+ size 906004192
model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5f63fd681941058333032c48fec221abd39546680955542e8b1e40ad89472a
3
+ size 906004192
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8d3ca4cd473b63a42c1ac3d53638ca6e70031f039893fc4772d868a78b8991
3
+ size 989923848
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df141ad9a7d70661c34333acd83fc22fc0299ac25fad090441e23d2b4212be4c
3
+ size 906004192
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9647cf90f011bd46c1abdeb884445cc5bb25be733d145b76cdcb9df5752a2c
3
+ size 906004184
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b373fdbbf41b088174f956588ea8e4f3359451b6b162fa1fe1a3812b28381b
3
+ size 906004176
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acefc5818cd0429f4fd30a8aec41ffe849bc2f2d75179bf89d4af4b33c03a92c
3
+ size 906004192
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48682bd9b1d4b3f73555884b393c8a078bfd54f3264d0e80ca183394adfbece
3
+ size 906004192
model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5ca102542e42fec0d4bfce832c541757176e9603cb81c29d480d1448c52636
3
+ size 989923848
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96b3f9470e0943b364898f3570b5833279b29b1e39bdc5e807d25e5188fe28d
3
+ size 906004192
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739b5f18e169b933caa601ea1a0810e058b1c51622ea519052e5b43c137065c4
3
+ size 906004192
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b062f8da3af09402b23346324bbec2bdfaa87fe44ddd18591a9aa169ca34d28
3
+ size 906004192
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60917459f2cde441e6eb37b98bd8bd3f9c98719c889b0977ad823e7a5b41dcc7
3
+ size 906004192
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0942ca6d242954ae330f8df270d6e0e8fdb5457db2917803b897603d14202bf7
3
+ size 906004192
model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569d8656710023b4a833b256ca6df59e6ecd87e28db9b9e4b6f4c62372686351
3
+ size 989923832
model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05a1a7e0bed49933361aa98ad69b72813e4fdbe1c781807d95ab5ef5f3330be
3
+ size 906004192
model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e878b9cad9d41a5812dc56c8d918e82d0c7684914339672cbc75303fb90a461
3
+ size 906004184
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecd26cb997be3834d0c34ca6ee17d4a3bfebc7ab127502820543281ddfec568
3
+ size 906004176
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e110dada671549e53d8c1035a4b38099e59733f7360157fa3472148fbaaf31d1
3
+ size 906004176
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448aaa6cfd62e9c072ab8b6d5acdfc74b0b47d73adc2700bca12d4e7dbbdcb02
3
+ size 906004176
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a36bd31535f7aeb347491cc3be0f4fe97e5af6271796f9ab1c4d811112535b
3
+ size 989923824
model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04bd3586e6ca014d211accc2fcdd196ecd14dafcc23b699d38a7443b71492b61
3
+ size 788571816
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00002-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00014-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00016-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00017-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00018-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00022-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00023-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00026-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 255,
41
+ "pad_token": "<s>",
42
+ "padding_side": "right",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "split_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }