Jacoby746 commited on
Commit
1004f51
1 Parent(s): 34664db

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:/Users/Jacoby/Downloads/text-generation-webui-main/models/BAAI_Infinity-Instruct-7M-Gen-mistral-7B",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 32,
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": 10000.0,
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": "float16",
29
+ "transformers_version": "4.44.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32002
32
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/BAAI_Infinity-Instruct-7M-Gen-mistral-7B
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/SanjiWatsuki_Kunoichi-7B
7
+ positive_prompts: ["You are a helpful roleplay assistant who is an expert at crafting engaging and interactive stories."]
8
+ - source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/uukuguy_speechless-instruct-mistral-7b-v0.2
9
+ positive_prompts: ["You are a creative assistant for crafting interesting and emotional experiences in roleplay."]
10
+
model-00001-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8a6bac4eb090204d3540e5eb4e257f387f78cd0bd3c6bd1071b04a591d1bed
3
+ size 933266864
model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e914bbf4539dbccc1e9c05149d9b997ad2fd0faf17fa6f545653fb669bd712f9
3
+ size 989890808
model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ed436502cf3c505e7586e805301ba7d3de15a41d9ecd09111838458b6ea5e5
3
+ size 905987664
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1700d3f60c0e8341767fcdebfb295bc6f52b278d309d582165dfec3675460ce1
3
+ size 905987664
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09154b5cc9291ad777c0fdd0c3efa83732a664680eebd691c7fad53c48e74ac4
3
+ size 905987664
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:146a72ab7d169faed8ff37cd4dd0fc726e435a432626da45657c7b52cf420cc7
3
+ size 905987664
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf5636fe4dab7748a0e6661847ab996f45a97fdb272ee3a6a3d3bd9577fb594
3
+ size 905987664
model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd9e95860f5090e7ab7977db699a1daf40e935a4cb5120a944a709f04ccf124b
3
+ size 989890808
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b218cd66979072444f4941e81b9a49961f627bdfa01da2bded70ad9bc03a40
3
+ size 905987664
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708773bded53058574fbd5afc8f81ab0285b98abf3dd72178f59d18aeeed6cad
3
+ size 905987672
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca5ee409ae4dd10067b6cf30028356fecf79ebff855de366b1278ae56582dd3
3
+ size 905987672
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230934e8dd08feaedc5e658609c433bc63584c6cb22f88012a9621a46f82f5ce
3
+ size 905987672
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0987eef8308ece3901b7f541f44dda0814d46e30de03354ead35fa8a810dc07b
3
+ size 905987672
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc04323a4729fa9affcf7b5d6a6d410c1390e47c5f746b179735b440aa2d103e
3
+ size 989890824
model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f13499707c9a2e2d42e2639dc9546fe83158f8d0bf3c5b6a3208f4adf925f7
3
+ size 905987672
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269201e67065c007ec9a9b711751ae650946102ee5927e2c1c64b96e28bcdb39
3
+ size 905987672
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187b1e8470156921ffd0bf78e0cc44ee58047394738d7ef4f9440dd8a700e212
3
+ size 905987672
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd92d80a2b95862ee50c159a858024da4d9bf6274903942dbbad5b0286b3d7f
3
+ size 905987672
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c6c3660c96e98197d7a49e41db749075f8b621b852f4e1074cbfb4027535d9
3
+ size 905987672
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89106e54ca123b4532d84a0595f2bfb82cd57a93f7df26828aed6906f28a456
3
+ size 989890824
model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e4962837856268f768eb500c03913a011642fb5ef35414809a719df90c932d
3
+ size 905987672
model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e0c74c5adb54cb584c6dd41782930d7afc8288ff86aa7f21e3fedcecacd7d9
3
+ size 905987672
model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778eddf3182f873e4bd894259ab13f01b9fc434cdfb9ddb76ee52edc563551aa
3
+ size 905987672
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505f4c1af58f92b060775e8d97dd217962814d7ed0e7a6caef0858c928bafbde
3
+ size 905987672
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1df957b7e6aa29af0c40c0a2790c136e8c0722206fe815402e421f690b201e
3
+ size 905987672
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0794814c508920e1c8ee78528932d31a0286b45438387642343bdefe2e7815c4
3
+ size 989890824
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e132f92357e013a2b7662348fa435eccfc81daa4f7ab9cfecbcf99c136d678a8
3
+ size 905987672
model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4081469c810ad68d198e9cac5621de9d74b9af6fd5c72411d0b34d6980c249
3
+ size 849900016
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 25758310400}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors", "lm_head.weight": "model-00028-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00028-of-00028.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": "<|im_end|>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "<s>",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "trust_remote_code": false,
59
+ "unk_token": "<unk>",
60
+ "use_default_system_prompt": true,
61
+ "use_fast": true
62
+ }