allknowingroger commited on
Commit
fe341f4
1 Parent(s): c38e7f3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
7
+ base_model:
8
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
9
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
10
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
11
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
12
+ - zhengr/MixTAO-7Bx2-MoE-v8.1
13
+ ---
14
+
15
+ # TaoPassthrough-15B-s
16
+
17
+ TaoPassthrough-15B-s is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
18
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
19
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
20
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
21
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
22
+ * [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
23
+
24
+ ## 🧩 Configuration
25
+
26
+ ```yaml
27
+ dtype: float16
28
+ merge_method: passthrough
29
+ slices:
30
+ - sources:
31
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
32
+ layer_range: [0,9]
33
+ - sources:
34
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
35
+ layer_range: [5,14]
36
+ - sources:
37
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
38
+ layer_range: [10,19]
39
+ - sources:
40
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
41
+ layer_range: [15,24]
42
+ - sources:
43
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
44
+ layer_range: [20,32]
45
+ ```
46
+
47
+ ## 💻 Usage
48
+
49
+ ```python
50
+ !pip install -qU transformers accelerate
51
+
52
+ from transformers import AutoTokenizer
53
+ import transformers
54
+ import torch
55
+
56
+ model = "allknowingroger/TaoPassthrough-15B-s"
57
+ messages = [{"role": "user", "content": "What is a large language model?"}]
58
+
59
+ tokenizer = AutoTokenizer.from_pretrained(model)
60
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
61
+ pipeline = transformers.pipeline(
62
+ "text-generation",
63
+ model=model,
64
+ torch_dtype=torch.float16,
65
+ device_map="auto",
66
+ )
67
+
68
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
69
+ print(outputs[0]["generated_text"])
70
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 48,
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
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.38.2",
29
+ "unsloth_version": "2024.1",
30
+ "use_cache": false,
31
+ "vocab_size": 32000
32
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ dtype: float16
3
+ merge_method: passthrough
4
+ slices:
5
+ - sources:
6
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
7
+ layer_range: [0,9]
8
+ - sources:
9
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
10
+ layer_range: [5,14]
11
+ - sources:
12
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
13
+ layer_range: [10,19]
14
+ - sources:
15
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
16
+ layer_range: [15,24]
17
+ - sources:
18
+ - model: zhengr/MixTAO-7Bx2-MoE-v8.1
19
+ layer_range: [20,32]
model-00001-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a167a83097b40d56a6beab788f118544968ae8421b4d7dbaa31df6a396ff348
3
+ size 1996640360
model-00002-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b9655ff7545d9b73a1d127b84b0e3dbadcfd27c35c87a4c3a7326308113487
3
+ size 1906404456
model-00003-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0577405765cd23c91f577a5f0430f5d8a8d247935847aba0793c8ddc17b15389
3
+ size 1996490944
model-00004-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3219c43c9f4f676e0126085e1a1cbef7119c9468648af7565277702f636d9af3
3
+ size 1996565664
model-00005-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5cc5aba52351ab72a8c7961fcfb32234eebc5f1dd571da6cbe6286908d31d4
3
+ size 1996524160
model-00006-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b219e3eb9d7fbd31b6686d286bf05e88dfa9897c44c18ae673b3a2463de762
3
+ size 1996532456
model-00007-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cac40c8a295c83c340cf055591d7f7bef5fb7f860bf510b72d7561e1cd8364e
3
+ size 1906321384
model-00008-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86665fdc5bf1f6293a240c89d1e290ce7ae8f02adef5617b8ec15f3a5f78da1b
3
+ size 1996499248
model-00009-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38464f822ebd895311d5785470758d0045f7640714a936e231feff7ceae58cf5
3
+ size 1996490952
model-00010-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da263285e3d9ce18a7fd4a3cc84243997efabc224946495e97ea6377c2ec548f
3
+ size 1996490952
model-00011-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02feba85471b77c9c5666a3965ac6620452907d44f16d058b75d32c8679c015a
3
+ size 1996490952
model-00012-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c82e606a96626a09536414d454cd94d9175d595ad819159921010745810335d
3
+ size 1996490944
model-00013-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e129f173053077f0063b7e45347d41387f8324bdc3d7ed1b04d956d5e472803e
3
+ size 1996490936
model-00014-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95bf3ff446fcde14054660b5f2e24138e996ff0244138ffa0bbcb2daf97c9e6
3
+ size 1996490944
model-00015-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca6c81017314b1a162a27628e1e865d9bec63bd2be6e6216132978fd01261ae
3
+ size 1996490952
model-00016-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644d7e684696a564aafb4865757e0832a14b6917d28a5f65dec2fd6d7ed370db
3
+ size 1996490952
model-00017-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22b62952cdaad616e24b3e99af9154b3b6226ba3aaf6614b854268fba7c1b05
3
+ size 1996524200
model-00018-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1764c4a0219c83b80d85d23885b470cdcc02c8ccffacf2cf233de1e4c2cd2f35
3
+ size 1996868328
model-00019-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5572e883f78a04d2505d398d95cadf080a7a697edebdc074999d48765bde2c
3
+ size 1997079272
model-00020-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0f6ec336d0e18d272e8aaf7b9ecc982585535c43c65cb7985cd3b8bba71663
3
+ size 620967416
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1", "total_size": 38375268352}, "weight_map": {"model.layers.19.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.embed_tokens.weight": "model-00002-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "lm_head.weight": "model-00007-of-00020.safetensors", "model.norm.weight": "model-00007-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00020-of-00020.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
+ }