mayacinka commited on
Commit
dbf12c4
1 Parent(s): 153d2e3

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2",
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": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
6
+ positive_prompts:
7
+ - "instructions"
8
+ - "concise"
9
+ - "straightforward"
10
+ - "helpful"
11
+ - "assistant"
12
+ negative_prompts:
13
+ - "vague"
14
+ - "inaccurate"
15
+ - "verbose"
16
+ - "complicated"
17
+ - "speculative"
18
+ - source_model: /home/Ubuntu/Desktop/mergekit/models/NeuralOmniWestBeaglake-7B
19
+ positive_prompts:
20
+ - "storytelling"
21
+ - "role play"
22
+ - "imagine"
23
+ - "artistic"
24
+ - "narrative"
25
+ - source_model: /home/Ubuntu/Desktop/mergekit/models/Kunoichi-DPO-v2-7B
26
+ positive_prompts:
27
+ - "reason"
28
+ - "think step by step"
29
+ - "logic"
30
+ - "knowledge"
31
+ negative_prompts:
32
+ - "artistic"
33
+ - "speculative"
34
+ - "playful"
35
+ - source_model: /home/Ubuntu/Desktop/mergekit/models/Starling-LM-7B-alpha
36
+ positive_prompts:
37
+ - "code"
38
+ - "python"
39
+ - "javascript"
40
+ - "react"
41
+ - "clear"
42
+ - "programming"
43
+ negative_prompts:
44
+ - "error"
45
+ - "art"
46
+ - "role play"
47
+
model-00001-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7556e7116d604e80145516203c76e9cf16c8d8622bddf8f4dccbc7951aeaf8db
3
+ size 1900046744
model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48931b170f4a2c7e55d5f3298791c20730fea437862c83ca5d1840b0b8467cfd
3
+ size 1929415992
model-00003-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59d2c51701fe49d82e5611c8583b92678eeb82130bcd8031406e495770185c4
3
+ size 1962953472
model-00004-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c47d84dd30ac367b4b95675b717f6ace5de1ed4920710fd3c478fa150f4e6b
3
+ size 1962953472
model-00005-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660a328f0164504ac12d5ede0b0fd8af4078d458373733ba9da37a8c6296d6c2
3
+ size 1929415992
model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231521aed136fd4b6ca5e3819aa5fc702abae0fc0d4f1b35fb57925921f874bd
3
+ size 1962953472
model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7998b5938010b4b82b23e6129ef0a44e3c08fefd9c21a088eba8cda10591cf
3
+ size 1962953472
model-00008-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b73c95596504e716a2f30264bfc65fd05685853d0f9ba697ca6e089206b481d
3
+ size 1929415960
model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d4c807439ff919cf07b25c70131bddd107c9be8cab0ba95fea20388ac6ba1e
3
+ size 1962953488
model-00010-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48902f126b479001ecd25b3076084aa0774a83b37338c4e432617525de077020
3
+ size 1962953488
model-00011-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03a6858c9812f820c47dba628e8f050eabc87fa90133bd83d12abd9370d5cdd
3
+ size 1996516344
model-00012-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06dea27cbaa29df8da15150cc5e882a6161e501b352415c6ba7ddd44b5fc9e63
3
+ size 1895853160
model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dc1af2affd6fc42d909417b8a854e58bab6dacfa04afcf3c188f815e6303a06
3
+ size 1962953488
model-00014-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d11067b4f37f3cf4d3744d739ba981bb93689d1910b4b403e296736dab314c
3
+ size 1962953488
model-00015-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0533bf523dac6031b9275a48dc055ee53801b06719e3601a4cd482f57f70dfc5
3
+ size 1929416016
model-00016-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6064d8bc0a6736bbf4fd52af4deb18e4af5d78dc1bdedc820d8be3257dcaacf
3
+ size 1962953488
model-00017-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e9e7717f9a849205fecd7859b373110fe33325bd73b5efea9ea818d74c0a77
3
+ size 1962953488
model-00018-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f136ce0eca7001d712aa0e31ff03e8404cc1eec992f734b91555d5ce11e7bc6d
3
+ size 1929416016
model-00019-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5fb036c632bcb4c08e2620501611f9c7a608302dc59c299fe13a305e27ab2d3
3
+ size 1962953488
model-00020-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d267ff0932cf7bcafd63e72680d5656062a0f921b26b9dbdbef470d6e7951d
3
+ size 1962953488
model-00021-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c034b509be233611020f4c737e51b655353fd8da244881b2843eb67bc8d63d29
3
+ size 1929416016
model-00022-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afda58a64db27f22d871739d6661d7d4825b6c0c218ebd6de950e06d06e6ca57
3
+ size 1962953488
model-00023-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:663e7882ad2931c0cc143534008ecb4d6b1aad5d0aa52d2e5de8b3d7148f2cf6
3
+ size 1962953488
model-00024-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd92711e56138d507356acb3dceb2b40dcc9a4de7f76e1c83d0d7590d5a8731
3
+ size 1996516344
model-00025-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4bdb7db964803d3e114cecf0167a412bb9e3ff3fb144914c7cd7ca5ed761a9
3
+ size 1460680264
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }