DenisTheDev commited on
Commit
843d860
1 Parent(s): 3c6d02a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 3,
20
+ "output_router_logits": false,
21
+ "pad_token_id": 2,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 10000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.0",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: HuggingFaceH4/zephyr-7b-beta
3
+ dtype: bfloat16
4
+ gate_mode: random
5
+ experts:
6
+ - source_model: openchat/openchat-3.5-0106
7
+ positive_prompts:
8
+ - "You are a helpful general-purpose assistant."
9
+ - "Hello!"
10
+ - "Who are you?"
11
+ - "I would want to visit Paris. What do you think?"
12
+ negative_prompts:
13
+ - "Give me a python code for the fastest sorting algorithm."
14
+ - "Tell me what's 8 to the power of 19."
15
+ - source_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
16
+ positive_prompts:
17
+ - "You are a helpful coding assistant."
18
+ - "Write me a java code for the fibonacci array."
19
+ - "I have an error in my python code."
20
+ negative_prompts:
21
+ - "Give me some tourism advices."
22
+ - "Write me poetry."
23
+ - "Tell me the result of 2 divided by 0.333"
24
+ - source_model: meta-math/MetaMath-Mistral-7B
25
+ positive_prompts:
26
+ - "You are an assistant good at math."
27
+ - "Tell me what is 2 times 46 equal?"
28
+ - "4 to the power of 62 is?"
29
+ negative_prompts:
30
+ - "Give me a recipe for spaghetti."
31
+ - "What locstions to you suggest visiting?"
32
+ - "Write me a simple cpp code."
33
+
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee466fdca968806aa3d5d093777569187cbb70ccb36f112b9480c67f5beaace
3
+ size 1933849936
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfece0ff33a385dd677a51f715baf5bb1ed0ace524127d26c86fd169baf70c6f
3
+ size 1996490952
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62dd0040a2beb84bcbcd5f8c031d138115192fe63400801eff3e7a7f2e36e0d0
3
+ size 1996490968
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb206b8c6f14001dbbb62a8d976e4840768f9cda551553c5d291f90e6ee8773d
3
+ size 1996490968
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f8a3fb9b986463462a80fc5a85ac0c64f8085c428aab1a75f36a4af30c172b
3
+ size 1996490968
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a032adc5331a8bd473c9c2c34aef68c3e61398a6784eace8431eda3c3a1a7223
3
+ size 1996490968
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e30948741b2248615f06c2aa051fd517154483721f4a9124800e6e43c7fb83
3
+ size 1996490952
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ca44e23a93874c89f0649ab421ac307a843012cb835e8ae5a7390a6152cd77
3
+ size 1996490952
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b880ea7181c9a64abfa19acabde7875aeb672ce60394127ee8aadf4cefac23
3
+ size 1996490968
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335af1312c2f0a42d4d167017c04f49616334b324796bb04c6ad8dd2d320f27a
3
+ size 1996490968
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5835812f64bee1b6268d4bd679925c3421f3d0327b028d25fda95ca161596cc
3
+ size 1996490968
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9cbb01c13682fd37e47b2654b6e0cdd26e5741c3a5d0267e434344788e4eb30
3
+ size 1996490960
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e92e10e92639235e24581ef1689cd381181f7bd3ec7a4c952e2cf419af63b24
3
+ size 1996490952
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a297412601b43f620d9493c2d2beb408e98a9754eb1a089ba87bbd80fdede7
3
+ size 1996490960
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b10c4308958fb2df74b77b00bf23c9939b3232d3e919123134e77605bfd657
3
+ size 1996490968
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d15661b18d1d7d04f7a1d403ac6cc4c4036f261e224eb44b1e8a1e767577707
3
+ size 1996490968
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea3d06efdd3e6a98ec28191606451832a528c686f353d0e1c5e772c4ddb8531
3
+ size 1996490968
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7a6cb10d94d42064cfe79e3f72310d5f45ea9aabfd51a5f49ef2f89a339552
3
+ size 1996765216
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097abcb4d137e4693d8a85ba89d8193eb245cf76319ce1ad47df1252ad23c829
3
+ size 1158423000
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.norm.weight": "model-00001-of-00019.safetensors", "lm_head.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }