shadowml commited on
Commit
5a1b8a9
1 Parent(s): c048fa7

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - mergekit
6
+ ---
7
+
8
+ # Mixolar-4x7b
9
+
10
+ This model is a Mixure of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
11
+ * [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
12
+ * [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)
13
+ * [rishiraj/meow](https://huggingface.co/rishiraj/meow)
14
+ * [kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2)
15
+
16
+ ## 🧩 Configuration
17
+
18
+ ```yaml
19
+ base_model: kyujinpy/Sakura-SOLAR-Instruct
20
+ gate_mode: hidden
21
+ experts:
22
+ - source_model: kyujinpy/Sakura-SOLAR-Instruct
23
+ positive_prompts:
24
+ - "chat"
25
+ - "assistant"
26
+ - "tell me"
27
+ - "explain"
28
+ negative_prompts:
29
+ - "mathematics"
30
+ - "reasoning"
31
+ - source_model: jeonsworld/CarbonVillain-en-10.7B-v1
32
+ positive_prompts:
33
+ - "write"
34
+ - "AI"
35
+ - "text"
36
+ - "paragraph"
37
+ negative_prompts:
38
+ - "mathematics"
39
+ - "reasoning"
40
+ - source_model: rishiraj/meow
41
+ positive_prompts:
42
+ - "chat"
43
+ - "say"
44
+ - "what"
45
+ negative_prompts:
46
+ - "mathematics"
47
+ - "reasoning"
48
+ - source_model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
49
+ positive_prompts:
50
+ - "reason"
51
+ - "math"
52
+ - "mathematics"
53
+ - "solve"
54
+ - "count"
55
+ negative_prompts:
56
+ - "chat"
57
+ - "assistant"
58
+ - "storywriting"
59
+ ```
60
+
61
+ ## 💻 Usage
62
+
63
+ ```python
64
+ !pip install -qU transformers bitsandbytes accelerate
65
+
66
+ from transformers import AutoTokenizer
67
+ import transformers
68
+ import torch
69
+
70
+ model = "mlabonne/Mixolar-4x7b"
71
+
72
+ tokenizer = AutoTokenizer.from_pretrained(model)
73
+ pipeline = transformers.pipeline(
74
+ "text-generation",
75
+ model=model,
76
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
77
+ )
78
+
79
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
80
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
81
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
82
+ print(outputs[0]["generated_text"])
83
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kyujinpy/Sakura-SOLAR-Instruct",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 48,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 4,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.36.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32000
34
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708a9fbf82acbfd611411d18f10f6ff6046321136f5fc5e064c62c844656e42d
3
+ size 9919946432
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0884c8dc71772e8c1ad4ca0c0b23fd31895f54a660218a68854be272b37cb4
3
+ size 9982454672
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b59a83a4ca016b9be1a1eea1fa81f548571fd4cf74f6519b192e73551798dc
3
+ size 9982454632
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664a6290b47f2fe63fcb0ae25f8d05a2c16ae44e268893176e6ecdc7a21f0572
3
+ size 9982454672
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b29df833d04c74e77ebc0b127181db9fabb16f698ceb9c7cb05dadbff029df
3
+ size 9982454640
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63c355ee5183abb8e21c6fdf0c8ef6684fa313e8206772efd509e781a6c1841
3
+ size 9982454672
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b5d4353c4550ca53900ef6ed5dbebefaeabb90bddebf02144dceb8bcc9fef1
3
+ size 9999635208
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb2bae0dd3e5d47fb6f0e9a056df8f079d70d137afe234933d5247ee63a7d72
3
+ size 2367182000
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }