lodrick-the-lafted commited on
Commit
9a6c41a
β€’
1 Parent(s): 6e7c948

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1--configuration_llama.LlamaConfig",
10
+ "AutoModel": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1--modeling_llama.LlamaModel",
11
+ "AutoModelForCausalLM": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1--modeling_llama.LlamaForCausalLM",
12
+ "AutoModelForSequenceClassification": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1--modeling_llama.LlamaForSequenceClassification"
13
+ },
14
+ "bos_token_id": 1,
15
+ "eos_token_id": 2,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 5120,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 13824,
20
+ "max_position_embeddings": 16384,
21
+ "model_type": "mixtral",
22
+ "num_attention_heads": 40,
23
+ "num_experts_per_tok": 2,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 40,
26
+ "num_local_experts": 2,
27
+ "output_router_logits": false,
28
+ "pad_token_id": 0,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "rope_theta": 1000000,
33
+ "router_aux_loss_coef": 0.001,
34
+ "sliding_window": null,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.37.0.dev0",
38
+ "use_cache": false,
39
+ "vocab_size": 32016
40
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: WhiteRabbitNeo/WhiteRabbitNeo-13B-v1
3
+ gate_mode: hidden
4
+ dtype: bfloat16
5
+
6
+ experts:
7
+ - source_model: WhiteRabbitNeo/WhiteRabbitNeo-13B-v1
8
+ positive_prompts: [""]
9
+
10
+ - source_model: Nexusflow/NexusRaven-V2-13B
11
+ positive_prompts: ["function calling", "tools"]
12
+
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-00005.safetensors", "model.norm.weight": "model-00001-of-00005.safetensors", "lm_head.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": "<s>",
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>",
67
+ "▁<PRE>",
68
+ "▁<MID>",
69
+ "▁<SUF>",
70
+ "▁<EOT>"
71
+ ],
72
+ "bos_token": "<s>",
73
+ "clean_up_tokenization_spaces": false,
74
+ "eos_token": "</s>",
75
+ "eot_token": "▁<EOT>",
76
+ "fill_token": "<FILL_ME>",
77
+ "legacy": null,
78
+ "middle_token": "▁<MID>",
79
+ "model_max_length": 1000000000000000019884624838656,
80
+ "pad_token": "<s>",
81
+ "prefix_token": "▁<PRE>",
82
+ "sp_model_kwargs": {},
83
+ "spaces_between_special_tokens": false,
84
+ "suffix_first": false,
85
+ "suffix_token": "▁<SUF>",
86
+ "tokenizer_class": "CodeLlamaTokenizer",
87
+ "trust_remote_code": false,
88
+ "unk_token": "<unk>",
89
+ "use_default_system_prompt": true,
90
+ "use_fast": true
91
+ }