opake commited on
Commit
1e0ef3a
1 Parent(s): ce91913

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BioMistral/BioMistral-7B",
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": "4.41.2",
29
+ "use_cache": false,
30
+ "vocab_size": 32000
31
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: BioMistral/BioMistral-7B
3
+ dtype: float16
4
+ gate_mode: cheap_embed
5
+ experts:
6
+ - source_model: epfl-llm/meditron-7b
7
+ positive_prompts: ["You are a helpful medical assistant."]
8
+ - source_model: medalpaca/medalpaca-7b
9
+ positive_prompts: ["You are assistant for medical question answering."]
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766c2adca42c4ba62e2a3fd86cf0f4d811c7d23500dfa0a959c77fe42044fd62
3
+ size 1967404816
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c901872a6fe68f51bd70f6de4f748632da20566961aab9c3ed976c3df25b96
3
+ size 1983908680
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5096381bdca520efe92acc48102527adc4e68d190baf0832085efc6bf5378f
3
+ size 1983908688
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec151aaa40d0ae43381110ce98f6ec8f21d80ac6a80bd594fc1e294f66a72610
3
+ size 1983908664
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4696d04f9dda1b750373e781cc9b592371938f06355da78e7b4361e24aba6cc
3
+ size 1983908680
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2d377d49e1ec83e2280984c761927b5f2abb9a5b39f07bd4080676f9102f55
3
+ size 1983908688
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9074f775a4806d5340010c2c18f272f418773c16fccd45a952f0299de613d6c
3
+ size 1983908664
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b2558ca9f60e64e40a026df468ac278f79b2b3c8f58318ab58c444f9f425b3
3
+ size 1983908688
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626714c70cfcdc3d04f423aaec7f9b660996841055ce0008cc46c48a3a16acfb
3
+ size 1984174512
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1feb5a0501061e77c09632d2903afe32a82f998895c66c53e242870b53633661
3
+ size 1979723880
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee1ded1ba738c69cf2c2f0cf36b3aa31e3576e76eed508d643ea44448679b15
3
+ size 705173504
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.norm.weight": "model-00001-of-00011.safetensors", "lm_head.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00011.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
+ }