ThomasComics commited on
Commit
021d40a
1 Parent(s): 3a709f3

Upload 27 files

Browse files
README.md CHANGED
@@ -1,3 +1,62 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - NousResearch/Nous-Hermes-2-Mistral-7B-DPO
10
+ - NeverSleep/Noromaid-7B-0.4-DPO
11
+ - mistralai/Mistral-7B-Instruct-v0.2
12
+ base_model:
13
+ - NousResearch/Nous-Hermes-2-Mistral-7B-DPO
14
+ - NeverSleep/Noromaid-7B-0.4-DPO
15
+ - mistralai/Mistral-7B-Instruct-v0.2
16
  ---
17
+
18
+ # Noro-Hermes-3x7B
19
+
20
+ Noro-Hermes-3x7B is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
21
+ * [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)
22
+ * [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)
23
+ * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
24
+
25
+ ## 🧩 Configuration
26
+
27
+ ```yaml
28
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
29
+ dtype: bfloat16
30
+ gate_mode: hidden
31
+ experts:
32
+ - source_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
33
+ positive_prompts: ["You are an intelligent assistant."]
34
+ - source_model: NeverSleep/Noromaid-7B-0.4-DPO
35
+ positive_prompts: ["You are a creative roleplaying assistant."]
36
+ - source_model: mistralai/Mistral-7B-Instruct-v0.2
37
+ positive_prompts: ["You are a general purpose assistant."]
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers bitsandbytes accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "ThomasComics/Noro-Hermes-3x7B"
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model)
52
+ pipeline = transformers.pipeline(
53
+ "text-generation",
54
+ model=model,
55
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
56
+ )
57
+
58
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
59
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
60
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
61
+ print(outputs[0]["generated_text"])
62
+ ```
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": 3,
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": "bfloat16",
27
+ "transformers_version": "4.39.1",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
3
+ dtype: bfloat16
4
+ gate_mode: hidden
5
+ experts:
6
+ - source_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
7
+ positive_prompts: ["You are an intelligent assistant."]
8
+ - source_model: NeverSleep/Noromaid-7B-0.4-DPO
9
+ positive_prompts: ["You are a creative roleplaying assistant."]
10
+ - source_model: mistralai/Mistral-7B-Instruct-v0.2
11
+ positive_prompts: ["You are a general purpose assistant."]
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce64ef5217abfe09f5ee9defdbfa8a60c72b01c833b544ff414a303be98e587d
3
+ size 1933849936
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4c24707a4658d7348e6eeb14121dee0cce1da4e064ab95b9904fffe9831e38
3
+ size 1996490952
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde1cfae23d1086ff56d52af3ca402bac795a21a041d944a1d1fc7013e7dab76
3
+ size 1996490968
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253388ec78a8616e9cb539aa5244564f391ec14f70bdd07be0351db507d5b532
3
+ size 1996490968
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c498caa789a1a879f39bef1a3b1a7cbb1d1c2fb7271b8ec68652b1c05299c8cf
3
+ size 1996490968
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bf31e196ba5ce5df8d3d4d6cedc38dd4fd172118d192b3014f081d3def49c2
3
+ size 1996490968
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d5908ad2349310d5a1ced5aa87c38e7b2674c83bec3c2e84c584fa1021430c
3
+ size 1996490952
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530b72d935133088a7b537ce4261c3463862d5bba927fd1b960122f3a24d504f
3
+ size 1996490952
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798b45fa1b36cbd8919caa4e9d3b8aca5c1c81bc390c2617d9effffcff7820f3
3
+ size 1996490968
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f2467f2ce6529fabe5ea2ea544e1b94a997ba37bc5391757c906e5a6fb1e19
3
+ size 1996490968
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5d3312e4f05066646b451d9168148d6e9c124f89454a71b592a6eb94797910
3
+ size 1996490968
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dfdfc8cf4b087829cf9bbed5e4a022a49f12718d45adc74cc14a0f54b09b298
3
+ size 1996490960
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6baef707deaa3451bf21bb4f37630a97ea27c6af4fc707ed83d58578bfc931c5
3
+ size 1996490952
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bbfb8a0804ee80e8eba60154c0ce683f60f200475b3a718149a61993b4d7fb
3
+ size 1996490960
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1dd92f88fe77949d7d8db2b0779316fd611d16bf235d7cca1c647751d5db196
3
+ size 1996490968
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046abb72d455c36d3900c28f03092eee6ce7cfbe746d07af12bf35f1d71fc80c
3
+ size 1996490968
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ebc6b2658b9d6e4137a4d5ffa3d2db9a91caff9ecb454b6d748faecbccd2b1
3
+ size 1996490968
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69bc58314efd6470015b935a93fc574161e76d3e83784e8d419dbc3eb7fd5f0
3
+ size 1996765216
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba006981e6296acea801fd074ae93d2208ec432b08fc0aeb512f61d957183906
3
+ size 1158423000
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.norm.weight": "model-00001-of-00019.safetensors", "lm_head.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.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
+ }