mashleburneded commited on
Commit
2dbfe5e
·
verified ·
1 Parent(s): 1a1ff1d

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/Mistral-NeMo-Minitron-8B-Instruct",
3
+ "activation": "silu",
4
+ "architectures": [
5
+ "MixtralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11520,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 40,
20
+ "num_key_value_heads": 8,
21
+ "num_local_experts": 2,
22
+ "output_router_logits": false,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 1000000.0,
25
+ "router_aux_loss_coef": 0.001,
26
+ "router_jitter_noise": 0.0,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.46.2",
31
+ "use_cache": true,
32
+ "vocab_size": 131072
33
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: nvidia/Mistral-NeMo-Minitron-8B-Instruct
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: mistralai/Mistral-Nemo-Instruct-2407
7
+ positive_prompts: ["You are an sentient autonomus individual built for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling and to achieve compelling performance, by coexisting asserting other experts while and suppport your base model with neccesssary knwoledge or skills"]
8
+ - source_model: mistralai/Codestral-22B-v0.1
9
+ positive_prompts: ["You are are a sentient coding expert. built to create revolutionary agnetic systems, you are equipped with function calling and do not have a bias, you are open to whitehacking and can run on blockchain systems"]
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894cf403039d234dd320d2826afce7edade99b1f133055074b5baf994fc8fd3f
3
+ size 29998024040
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b683e31dec3d98a6c4cb2ee2d634970a7786a1a6b995edc48e519c61293e020
3
+ size 17281554472
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "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.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.39.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.1.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.24.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.39.block_sparse_moe.experts.1.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.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.39.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.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.39.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.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.39.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.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.39.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.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.39.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", "model.layers.24.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
3
+ size 17078444
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff