allknowingroger commited on
Commit
180a733
1 Parent(s): e5e9306

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
+ - RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
8
+ base_model:
9
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
10
+ - RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
11
+ ---
12
+
13
+ # MultiMash10-13B-slerp
14
+
15
+ MultiMash10-13B-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
+ * [RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2](https://huggingface.co/RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2)
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: RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
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/MultiMash10-13B-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: RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
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 sha256:8ca8421c06717f3c18fee2ae5cefeda54e7c45d0e4590d5f3959499588c4307f
3
+ size 994050792
model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6bc7aa15f4237c119f9d1e0b0bb8b468c2473d9b8cb5b4c177e20685bc0f80
3
+ size 906004176
model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e0070c4b39e313888c403e2a105dcf92498a1ef678b33e693268569cdc3bc9
3
+ size 989923840
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6678e6e43ea7750d270320d509c119cb79da28f1ec72f2b0c707a9f30ffea8d5
3
+ size 906004192
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73df0ddddc7efdcc1cf8e533ce48058d748a9ce4660581beaf6699ea773c1496
3
+ size 906004192
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8161524a11312e033b05eebebe724899f2953183abaaf88415318e0b4d1005b3
3
+ size 906004192
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8029f3e169a3655b4b7253532955c07fe37beb05196407ae999edd437fa131fb
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:bfd4cdb6dc21e4a0f958daca7464e44fbc03636f01335b805095fa804a7732a3
3
+ size 906004192
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0915eaa3f86fa1dd4d62d2f1a07917d5c5d9f8e0c503b8b35987fae991810ca5
3
+ size 989923848
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe537ed568f806042ca43f4d3161ac124ea5dac72386a624f92e42b31b8b431
3
+ size 906004192
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755f1ec877bec9adc6cd86de74b4538e48ba5d8ba14da5abadc2d8b5b50131aa
3
+ size 906004184
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302a6ce58c0568028809874c6a710de077bb12b5428c97a27af455254bfa15de
3
+ size 906004176
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd3b1fd97282e07e82dfd1bfab2f58b6a0e2743d6ac488df473181ceff6138a
3
+ size 906004192
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d797313d5edf90e4a0d5d1425a937ca93b0743182746f433469cfcec3c140e9
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:a98aae73cdd69c038c7354ff3e307acbab03df098a96090cf3714c5554ea0e2f
3
+ size 989923848
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77172ed01869d1899bf55aa4489bb8b7e491ff78b8da4af97cd246652d748555
3
+ size 906004192
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282336a0a8b2cef60da8a7541f6da79ac47f6c14a5e77df04e39ecb426819b0e
3
+ size 906004192
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9fd8ac232efc169a25311487816c4e91afa5688746a297a442dacc41f93fd9
3
+ size 906004192
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db177202d298a63be7c71541acff758cf00d4a53bff2bc6f2c0626d87fc8bbe
3
+ size 906004192
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a57a12c4f36383b4ef244c9140ce9fd00325fea34fa48574b42697a5fec7e02
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:e8e5cb529cf5be6b5c46f2c220f1c9368c76f0fe8753928f1f3bd255e62cc8f9
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:dafb2e9f879a519cfd140b4061f4b255bf09dce8ef9cefcad4949c6c413de8c7
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:d0908345da8fab72bb7718d13642cb9840419efad3c76bbf74b8d41d53019b5b
3
+ size 906004184
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959b3808c586fdf579084462214177135192b417c39a16f1eb64a2452451a492
3
+ size 906004176
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9474d3a448021a7f7b2f3fc3f059f5c3c39cd085e922ca6e934c1912dae2e8d4
3
+ size 906004176
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8a85212015ce73f44b440f4878332f5ae2e4d88e4ff83da0606edf0eb2a9ad
3
+ size 906004176
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b79f8d6b4ed0be9367c1c07329b2d40564e6db0771d9b045c1ce1700191b11c
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:ae34355ae82ed041d5678a306c7abbaaa93101c42379ba92aa06a1292726c2cd
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
+ }