Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +61 -0
- config.json +29 -0
- mergekit_config.yml +30 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +357 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- WesPro/C4AI_Adventure_CaptainCommand08_32B
|
4 |
+
- TheDrummer/Star-Command-R-32B-v1
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# merge
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the SLERP merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [WesPro/C4AI_Adventure_CaptainCommand08_32B](https://huggingface.co/WesPro/C4AI_Adventure_CaptainCommand08_32B)
|
24 |
+
* [TheDrummer/Star-Command-R-32B-v1](https://huggingface.co/TheDrummer/Star-Command-R-32B-v1)
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
slices:
|
32 |
+
- sources:
|
33 |
+
- model: TheDrummer/Star-Command-R-32B-v1
|
34 |
+
layer_range:
|
35 |
+
- 0
|
36 |
+
- 40
|
37 |
+
- model: WesPro/C4AI_Adventure_CaptainCommand08_32B
|
38 |
+
layer_range:
|
39 |
+
- 0
|
40 |
+
- 40
|
41 |
+
merge_method: slerp
|
42 |
+
base_model: TheDrummer/Star-Command-R-32B-v1
|
43 |
+
parameters:
|
44 |
+
t:
|
45 |
+
- filter: self_attn
|
46 |
+
value:
|
47 |
+
- 0
|
48 |
+
- 0.5
|
49 |
+
- 0.3
|
50 |
+
- 0.7
|
51 |
+
- 1
|
52 |
+
- filter: mlp
|
53 |
+
value:
|
54 |
+
- 1
|
55 |
+
- 0.5
|
56 |
+
- 0.7
|
57 |
+
- 0.3
|
58 |
+
- 0
|
59 |
+
- value: 0.5
|
60 |
+
dtype: bfloat16
|
61 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TheDrummer/Star-Command-R-32B-v1",
|
3 |
+
"architectures": [
|
4 |
+
"CohereForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 5,
|
9 |
+
"eos_token_id": 255001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 24576,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"logit_scale": 0.0625,
|
16 |
+
"max_position_embeddings": 131072,
|
17 |
+
"model_type": "cohere",
|
18 |
+
"num_attention_heads": 64,
|
19 |
+
"num_hidden_layers": 40,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 4000000,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"use_qk_norm": false,
|
28 |
+
"vocab_size": 256000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: TheDrummer/Star-Command-R-32B-v1
|
4 |
+
layer_range:
|
5 |
+
- 0
|
6 |
+
- 40
|
7 |
+
- model: WesPro/C4AI_Adventure_CaptainCommand08_32B
|
8 |
+
layer_range:
|
9 |
+
- 0
|
10 |
+
- 40
|
11 |
+
merge_method: slerp
|
12 |
+
base_model: TheDrummer/Star-Command-R-32B-v1
|
13 |
+
parameters:
|
14 |
+
t:
|
15 |
+
- filter: self_attn
|
16 |
+
value:
|
17 |
+
- 0
|
18 |
+
- 0.5
|
19 |
+
- 0.3
|
20 |
+
- 0.7
|
21 |
+
- 1
|
22 |
+
- filter: mlp
|
23 |
+
value:
|
24 |
+
- 1
|
25 |
+
- 0.5
|
26 |
+
- 0.7
|
27 |
+
- 0.3
|
28 |
+
- 0
|
29 |
+
- value: 0.5
|
30 |
+
dtype: bfloat16
|
model-00001-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e47e7d564ceef3b94e87831092a1ebbfac4bfab1f6b33b1894faf5308909485a
|
3 |
+
size 4999627232
|
model-00002-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f77e527a0d26587deeb36035a9ab27fcca9cc3fd70a658dd18fd078f8386cea
|
3 |
+
size 4949330904
|
model-00003-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:333272db00aaecd6b7e8f9d7ec4b8b950969f7bccd421fe3aad98829901d6985
|
3 |
+
size 4815129808
|
model-00004-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b1cfd1176c6569e081180558e4325138fce7ca4e226b661e3e017a4305d63ef
|
3 |
+
size 4932553592
|
model-00005-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d75423124d8c3134f3ed8127f10dc1e77e44c396cf94ed9024a158e704ac603e
|
3 |
+
size 4932553584
|
model-00006-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cb010a2758757ad43a739144d8db6fc9177882cbd68c5e2cb26679ac6e4b5f2
|
3 |
+
size 4949330920
|
model-00007-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5d983f7f199e437f64c3348d04d6f5a62e47c49322d4860fe823ed6984dc092
|
3 |
+
size 4815129808
|
model-00008-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eebf39c31810a23d593a778c4cbe8d8fc966778245db0c73630478417d39f8a1
|
3 |
+
size 4932553592
|
model-00009-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9691c8ed7d516a8b5bbcb954b07b72c5959f39341c520f23ceebcbe2745a49b6
|
3 |
+
size 4932553584
|
model-00010-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07bea0baa91599b7d06b0bf1da03ceda51dee7f665ed12ea7816bd836a8f10f3
|
3 |
+
size 4949330920
|
model-00011-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:219fda9209f92b2d038553e1c7c40af115db410a81f5516efe0ee036b625a2ad
|
3 |
+
size 4815129808
|
model-00012-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3c9ad72638f4825f1e8706a4d6df6ab09b0d5c2ce5413e6b8a8db9731ff4635
|
3 |
+
size 4932553576
|
model-00013-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d16cf0b04f961000d274ef426ecb598a8202a251433d68d42e8b0333f5ebf50
|
3 |
+
size 4932553560
|
model-00014-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7514a0ffd50e5b7cec3460c66b963d7eca1d3d19f1d2d6254d746662d3b7667
|
3 |
+
size 704660152
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 64592953344}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<BOS_TOKEN>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<PAD>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2969ae78126f0595868bb928431b64e1381d0a855b1c6a6c7b167184db7fbfe7
|
3 |
+
size 20125113
|
tokenizer_config.json
ADDED
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<PAD>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<UNK>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<CLS>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "<SEP>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "<MASK_TOKEN>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"5": {
|
47 |
+
"content": "<BOS_TOKEN>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"6": {
|
55 |
+
"content": "<EOS_TOKEN>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"7": {
|
63 |
+
"content": "<EOP_TOKEN>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"255000": {
|
71 |
+
"content": "<|START_OF_TURN_TOKEN|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"255001": {
|
79 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"255002": {
|
87 |
+
"content": "<|YES_TOKEN|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"255003": {
|
95 |
+
"content": "<|NO_TOKEN|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"255004": {
|
103 |
+
"content": "<|GOOD_TOKEN|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"255005": {
|
111 |
+
"content": "<|BAD_TOKEN|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"255006": {
|
119 |
+
"content": "<|USER_TOKEN|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"255007": {
|
127 |
+
"content": "<|CHATBOT_TOKEN|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"255008": {
|
135 |
+
"content": "<|SYSTEM_TOKEN|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"255009": {
|
143 |
+
"content": "<|USER_0_TOKEN|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"255010": {
|
151 |
+
"content": "<|USER_1_TOKEN|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"255011": {
|
159 |
+
"content": "<|USER_2_TOKEN|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"255012": {
|
167 |
+
"content": "<|USER_3_TOKEN|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"255013": {
|
175 |
+
"content": "<|USER_4_TOKEN|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"255014": {
|
183 |
+
"content": "<|USER_5_TOKEN|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"255015": {
|
191 |
+
"content": "<|USER_6_TOKEN|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"255016": {
|
199 |
+
"content": "<|USER_7_TOKEN|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"255017": {
|
207 |
+
"content": "<|USER_8_TOKEN|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"255018": {
|
215 |
+
"content": "<|USER_9_TOKEN|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"255019": {
|
223 |
+
"content": "<|EXTRA_0_TOKEN|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"255020": {
|
231 |
+
"content": "<|EXTRA_1_TOKEN|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"255021": {
|
239 |
+
"content": "<|EXTRA_2_TOKEN|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"255022": {
|
247 |
+
"content": "<|EXTRA_3_TOKEN|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"255023": {
|
255 |
+
"content": "<|EXTRA_4_TOKEN|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"255024": {
|
263 |
+
"content": "<|EXTRA_5_TOKEN|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"255025": {
|
271 |
+
"content": "<|EXTRA_6_TOKEN|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"255026": {
|
279 |
+
"content": "<|EXTRA_7_TOKEN|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"255027": {
|
287 |
+
"content": "<|EXTRA_8_TOKEN|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"255028": {
|
295 |
+
"content": "<|NEW_FILE|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"255029": {
|
303 |
+
"content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"255030": {
|
311 |
+
"content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"255031": {
|
319 |
+
"content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"255032": {
|
327 |
+
"content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"255033": {
|
335 |
+
"content": "<|EXTRA_9_TOKEN|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": false
|
341 |
+
}
|
342 |
+
},
|
343 |
+
"bos_token": "<BOS_TOKEN>",
|
344 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}",
|
345 |
+
"clean_up_tokenization_spaces": false,
|
346 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
347 |
+
"legacy": true,
|
348 |
+
"merges_file": null,
|
349 |
+
"model_max_length": 1000000000000000019884624838656,
|
350 |
+
"pad_token": "<PAD>",
|
351 |
+
"sp_model_kwargs": {},
|
352 |
+
"spaces_between_special_tokens": false,
|
353 |
+
"tokenizer_class": "CohereTokenizer",
|
354 |
+
"unk_token": null,
|
355 |
+
"use_default_system_prompt": false,
|
356 |
+
"vocab_file": null
|
357 |
+
}
|