burak commited on
Commit
30b997b
1 Parent(s): ccb77d3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ ---
8
+
9
+ # Turkish-moe
10
+
11
+ Turkish-moe is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
12
+
13
+ ## 🧩 Configuration
14
+
15
+ ```yaml
16
+ base_model: Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0
17
+ dtype: float16
18
+ gate_mode: cheap_embed
19
+ experts:
20
+ - source_model: TURKCELL/Turkcell-LLM-7b-v1
21
+ positive_prompts: ["You are an helpful general-pupose assistant."]
22
+ - source_model: Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0
23
+ positive_prompts: ["You are helpful assistant."]
24
+
25
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0",
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": 2,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.40.1",
29
+ "use_cache": true,
30
+ "vocab_size": 44312
31
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: TURKCELL/Turkcell-LLM-7b-v1
7
+ positive_prompts: ["You are an helpful general-pupose assistant."]
8
+ - source_model: Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0
9
+ positive_prompts: ["You are helpful assistant."]
10
+
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16313f65e6424ab6926e1f57283fc05efd713564852dcaa8ff25a1dd5fd96cbd
3
+ size 1900688416
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee38a79d1fb1bbfe34aaca128889b3a6a6fa3d32049e4e14ec4fc78070e2a5d
3
+ size 1996490936
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f11e4c1ff5eeb11fc0979e0c4322b655effd25b40ba5056662e59c608dd78a
3
+ size 1996490952
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a27d08e35f2b2f9cfe8891d1009144df9134f05579e1fe8a7cbcc67d53c6a6b
3
+ size 1996490952
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aace1f7ee459bae5e2046cffea7fd84834451bf30aaf4ce383ac69d8519f5821
3
+ size 1996490936
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8b35d4c35c72444daac641af97bd19607c48151d5ce393ab3bad767ef63081
3
+ size 1996490944
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4121626d6b4fe4fb00d11c051a4b5ec93a1ea909401c857fbfa3da85e999701
3
+ size 1996490952
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3270fc2d30d76075eb364025a39f763dbb7a0e1382466902e1a4db1cad5bf54
3
+ size 1996490952
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87453e608fc2c71c0d250d1febccbe9443f790ffb214bcffbbffc1e658e5053f
3
+ size 1996490936
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2abc137e53046795b98c43924924f70ef6c930d683e2f34184675814c3bcce
3
+ size 1996490944
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffb79b48fbecf7950c9b1e93589564b39e6bcb4062448be217a32029ebcfe61
3
+ size 1996490952
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7670f3b47e2e20ce3026398095e0d835027576b458210b87468e6ee9f1445a6a
3
+ size 1979980960
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9babc52972e6d7cc0c38acfc700c2f15ff8877e37608e0ea093af3c60cbce8c
3
+ size 1979723896
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d34a5e3d561b420561350bd0fc485df13b4b7d0b70004b25018ff518fd81032
3
+ size 134746088
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.norm.weight": "model-00001-of-00014.safetensors", "lm_head.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00014-of-00014.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:c1f2e58f6adbcc203ed4c87b87ed6308abb35e3f854d371c71bd798c9097c724
3
+ size 712489
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ },
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": 2048,
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
+ "use_fast": true
44
+ }