mvpmaster commited on
Commit
30e1c40
1 Parent(s): bb892b2

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp
10
+ - mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp
11
+ base_model:
12
+ - mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp
13
+ - mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp
14
+ ---
15
+
16
+ # Einstein-4D-MoE-2x7b-test
17
+
18
+ Einstein-4D-MoE-2x7b-test is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp](https://huggingface.co/mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp)
20
+ * [mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp](https://huggingface.co/mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp)
21
+
22
+ ## 🧩 Configuration
23
+
24
+
25
+ ## 💻 Usage
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mvpmaster/Einstein-4D-Marcoro14-7b-full-slerp",
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
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: mvpmaster/Einstein-4D-Marcoro14-7b-full-slerp
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp
7
+ positive_prompts: ["You a helpful assistant in code and main question answering"]
8
+ - source_model: mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp
9
+ positive_prompts: ["You are assistant for math geometry and creative answers"]
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94050bc6c5c04deddfa1ba0539ff854ab5c4deb2de74ebe9dd61fdd3320f34cf
3
+ size 1983949880
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6993974f1914d83aab696d32a30d250cb04bb00027dfd51eac7bbd027e6fdff
3
+ size 1895878464
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93027fa1018cf0caf1b231f553a24c46a129956fafdad2cedf865b170ec7d34
3
+ size 1929415960
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c47299568ef23b4cc15ebb004ee1f21802c45c528bc908d588c9d8db32943d
3
+ size 1895878472
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1776d2ad9f180ad90c969d050aa30199612a2576845ca75c54cf70b7ba6fb9b7
3
+ size 1929415976
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a07ff70961b2900cb558af4dc72b8af518e6671ddd22eb5bb4c4aa8a8de04f3
3
+ size 1979756288
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7540c3f7fb13210f3d998c1bc51af1e22248ac37006a1b0262a37206e667911e
3
+ size 1962978848
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0abe061380e4cc53b01c7c2facaf48ea016101ec86954b7726c339bc95daee3
3
+ size 1979756288
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179424309d0ef8f5222333011d55bef2e71a6598a9863f2f4f6bbe4a6127e4b3
3
+ size 1962978848
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7632368c8685e46c0aa5a4277cf387e7862aee5966280d5c850b08b18b3d155f
3
+ size 1979756288
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5eb771f44b9fd2fc93469130fcd23f9f22b33f596b6cc507f599dc26883f00
3
+ size 1962978848
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dba0dfdd6ddae0119b716f2f3374584ff8d1a246d75d267869619ac8a1e1a2
3
+ size 1979756288
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a85c641241c11046615163e8ca31567cae84c2c92e69fdf470c34a4bad0a2f5
3
+ size 1962978848
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3de2460ba70d814fc0b4531c5a62409a62ee07da92e58bbb67ed7876d1c448
3
+ size 352849816
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-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.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_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.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.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.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.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.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.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.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.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.27.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.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.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<s>",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }