AmeerH commited on
Commit
f985cad
1 Parent(s): bdf6d96

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - mistralai/Mistral-7B-Instruct-v0.2
10
+ - meta-math/MetaMath-Mistral-7B
11
+ base_model:
12
+ - mistralai/Mistral-7B-Instruct-v0.2
13
+ - meta-math/MetaMath-Mistral-7B
14
+ ---
15
+
16
+ # Mistral-Math-2x7b-mix
17
+
18
+ Mistral-Math-2x7b-mix is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
20
+ * [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
26
+ dtype: float16
27
+ gate_mode: cheap_embed
28
+ experts:
29
+ - source_model: mistralai/Mistral-7B-Instruct-v0.2
30
+ positive_prompts: ["You are helpful assistant."]
31
+ - source_model: meta-math/MetaMath-Mistral-7B
32
+ positive_prompts: ["You are an assistant good at math."]
33
+ ```
34
+
35
+ ## 💻 Usage
36
+
37
+ ```python
38
+ !pip install -qU transformers bitsandbytes accelerate
39
+
40
+ from transformers import AutoTokenizer
41
+ import transformers
42
+ import torch
43
+
44
+ model = "AmeerH/Mistral-Math-2x7b-mix"
45
+
46
+ tokenizer = AutoTokenizer.from_pretrained(model)
47
+ pipeline = transformers.pipeline(
48
+ "text-generation",
49
+ model=model,
50
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
51
+ )
52
+
53
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
54
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
55
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
56
+ print(outputs[0]["generated_text"])
57
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
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
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: mistralai/Mistral-7B-Instruct-v0.2
7
+ positive_prompts: ["You are helpful assistant."]
8
+ - source_model: meta-math/MetaMath-Mistral-7B
9
+ positive_prompts: ["You are an assistant good at math."]
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b27ee1264e2ddbc5ab661670331cf614483e8b5063a8aa7e58280ff4badcfa
3
+ size 1933849864
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f824bf9a10fa9787db8285d8f84a619856a419c27828eaf113190007121ed5e5
3
+ size 1996490944
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc4db9a6897ba8f97cc2ef0602a0199dec8ce745ea8e788c75ac723aac26f4c
3
+ size 1996490952
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0443a77bf4dbc636aa2e7f0483fcf3c25ba7c97a0edc76c6384a5245fed733
3
+ size 1996490952
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864caf924416bcdb98d558ef010b9ef7c49f067f31654106fe279e886e631fe0
3
+ size 1996490936
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d6364bf5ebb57165bdfe6bc66ea1107f4bf024d84f50e2182ed24a99d9aacf
3
+ size 1996490944
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545c413b5d378a586b518b9b4c9a161ec630e06e5326a56318351bde049996bd
3
+ size 1996490952
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d12907e1a3fa9f3baaf0fdd26073235990b907aab0c1ec82901f6a421606afe9
3
+ size 1996490944
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97be4fe208dfe5ce2023ae698ef35f0de3176211d5bce73113bd5a84936f3dbf
3
+ size 1996490936
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc09460a1a48f5ec771cdf78d945483b256e748dc0ebacee7dc30716bedf2b0
3
+ size 1996490952
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43894c22eb27774a29f321f225c92655f5e18fc8f2daa1426844ee65bc9f353d
3
+ size 1996490952
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614d45351f535e0732f550a3088fc0aa6cde72259c8352e2101559bace989b43
3
+ size 1979981504
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f671b094d4da25a2ab38c9cb8aa203b663efbe0c7d2b711b6acfdc8a41ab64
3
+ size 1879588280
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }