Delta-Vector commited on
Commit
dab567f
·
verified ·
1 Parent(s): 7bf072a

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/mergekit_moe_config-checkpoint.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: unsloth/Mistral-Small-Instruct-2409
2
+ gate_mode: hidden
3
+ experts_per_token: 2
4
+ experts:
5
+ - source_model: unsloth/Mistral-Small-Instruct-2409
6
+ positive_prompts:
7
+ - "chat"
8
+ - "assistant"
9
+ - "tell me"
10
+ - "explain"
11
+ - "I want"
12
+ - "show me"
13
+ - "touch"
14
+ - "believe"
15
+ - "see"
16
+ - "love"
17
+ - source_model: invisietch/MiS-Firefly-v0.2-22B
18
+ positive_prompts:
19
+ - "storywriting"
20
+ - "write"
21
+ - "scene"
22
+ - "story"
23
+ - "character"
24
+ - "sensual"
25
+ - "sexual"
26
+ - "horny"
27
+ - "turned on"
28
+ - "intimate"
29
+ dtype: bfloat16
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Mistral-Small-Instruct-2409",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 6144,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 16384,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 48,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 56,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.48.3",
30
+ "use_cache": true,
31
+ "vocab_size": 32768
32
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: unsloth/Mistral-Small-Instruct-2409
2
+ gate_mode: hidden
3
+ experts_per_token: 2
4
+ experts:
5
+ - source_model: unsloth/Mistral-Small-Instruct-2409
6
+ positive_prompts:
7
+ - "chat"
8
+ - "assistant"
9
+ - "tell me"
10
+ - "explain"
11
+ - "I want"
12
+ - "show me"
13
+ - "touch"
14
+ - "believe"
15
+ - "see"
16
+ - "love"
17
+ - source_model: invisietch/MiS-Firefly-v0.2-22B
18
+ positive_prompts:
19
+ - "storywriting"
20
+ - "write"
21
+ - "scene"
22
+ - "story"
23
+ - "character"
24
+ - "sensual"
25
+ - "sexual"
26
+ - "horny"
27
+ - "turned on"
28
+ - "intimate"
29
+ dtype: bfloat16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8455779e87af122c73b7fd5448a02333ac94dfdcca1ef316951c422108f21f31
3
+ size 9865715928
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d800cac74863ec2c96e7742f02440864d2af8068d655bc924abe1d2aba21c44
3
+ size 9865009504
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c1e3c5762633fd24a8a2b0225d98a4d5df637f6f9d667087be31d4f40fd576
3
+ size 9865009480
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abeb814efb7a7895e1b9a44b6e0b807338ddb969f7c426fa3b6f0a10b7dd0763
3
+ size 9865009504
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84495910ad78f6d2f7e4a087d080e6092bcf2decbb6f8dd0c52419be906d775d
3
+ size 9865009488
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93d4e5c10f8d78dbc4ff84ac64d07f28dbe55112ba45647cfbf85163342009c
3
+ size 9865009496
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55349f4ac8594abd2b44c86f3a91c033e82dd0a0f6e4a47e256f0e584c9ae3f9
3
+ size 9941202448
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c394653dee64229f6c4024878be44a9bfa80bcb38ee1416bafb011c70d48e956
3
+ size 9186934024
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff