SanjiWatsuki commited on
Commit
a24af6d
1 Parent(s): 35bc691

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ ---
8
+
9
+ # DeepSeek-Coder-Instruct-8x1.3b
10
+
11
+ DeepSeek-Coder-Instruct-8x1.3b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
12
+
13
+ ## 🧩 Configuration
14
+
15
+ ```yaml
16
+ base_model: deepseek-ai/deepseek-coder-1.3b-instruct
17
+ gate_mode: random
18
+ dtype: bfloat16
19
+ experts:
20
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
21
+ positive_prompts: [""]
22
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
23
+ positive_prompts: [""]
24
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
25
+ positive_prompts: [""]
26
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
27
+ positive_prompts: [""]
28
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
29
+ positive_prompts: [""]
30
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
31
+ positive_prompts: [""]
32
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
33
+ positive_prompts: [""]
34
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
35
+ positive_prompts: [""]
36
+ ```
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32021,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 16,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "num_local_experts": 8,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": {
25
+ "factor": 4.0,
26
+ "type": "linear"
27
+ },
28
+ "rope_theta": 100000,
29
+ "router_aux_loss_coef": 0.001,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.37.0.dev0",
34
+ "use_cache": true,
35
+ "vocab_size": 32256
36
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: deepseek-ai/deepseek-coder-1.3b-instruct
3
+ gate_mode: random
4
+ dtype: bfloat16
5
+ experts:
6
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
7
+ positive_prompts: [""]
8
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
9
+ positive_prompts: [""]
10
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
11
+ positive_prompts: [""]
12
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
13
+ positive_prompts: [""]
14
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
15
+ positive_prompts: [""]
16
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
17
+ positive_prompts: [""]
18
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
19
+ positive_prompts: [""]
20
+ - source_model: deepseek-ai/deepseek-coder-1.3b-instruct
21
+ positive_prompts: [""]
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9a3df20410e2a2f753018b88afa99845c4d5510779affaa52208e94f296aba
3
+ size 9981032240
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9b2a98955cd6cd411fb3687fb57322bc5efc72416ee087fab53b48c0e35a94
3
+ size 4075162648
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.norm.weight": "model-00001-of-00002.safetensors", "lm_head.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|EOT|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|begin▁of▁sentence|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "32000": {
6
+ "content": "õ",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "32001": {
14
+ "content": "÷",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "32002": {
22
+ "content": "Á",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32003": {
30
+ "content": "ý",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32004": {
38
+ "content": "À",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32006": {
54
+ "content": "ø",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32007": {
62
+ "content": "ú",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32008": {
70
+ "content": "þ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32009": {
78
+ "content": "ü",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32010": {
86
+ "content": "ù",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32011": {
94
+ "content": "ö",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32012": {
102
+ "content": "û",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32013": {
110
+ "content": "<|begin▁of▁sentence|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32014": {
118
+ "content": "<|end▁of▁sentence|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32015": {
126
+ "content": "<|fim▁hole|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32016": {
134
+ "content": "<|fim▁begin|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32017": {
142
+ "content": "<|fim▁end|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32018": {
150
+ "content": "<pad>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32019": {
158
+ "content": "<|User|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32020": {
166
+ "content": "<|Assistant|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32021": {
174
+ "content": "<|EOT|>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "bos_token": "<|begin▁of▁sentence|>",
183
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|EOT|>",
186
+ "legacy": true,
187
+ "model_max_length": 16384,
188
+ "pad_token": "<|begin▁of▁sentence|>",
189
+ "sp_model_kwargs": {},
190
+ "tokenizer_class": "LlamaTokenizer",
191
+ "unk_token": null,
192
+ "use_default_system_prompt": false
193
+ }