Text Generation
Transformers
Safetensors
mixtral
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
Locutusque/TinyMistral-248M-v2
Locutusque/TinyMistral-248M-v2.5
Locutusque/TinyMistral-248M-v2.5-Instruct
jtatman/tinymistral-v2-pycoder-instruct-248m
Felladrin/TinyMistral-248M-SFT-v4
Locutusque/TinyMistral-248M-v2-Instruct
text-generation-inference
Inference Endpoints
Locutusque
commited on
Commit
•
cd02536
1
Parent(s):
74e98a0
Upload 5 files
Browse files- config.json +3 -3
- generation_config.json +6 -0
- special_tokens_map.json +7 -1
- tokenizer.json +6 -8
- tokenizer_config.json +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
@@ -23,8 +23,8 @@
|
|
23 |
"router_aux_loss_coef": 0.001,
|
24 |
"sliding_window": null,
|
25 |
"tie_word_embeddings": false,
|
26 |
-
"torch_dtype": "
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32005
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/media/sebastian/T7/Projects/saved_models",
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
|
|
23 |
"router_aux_loss_coef": 0.001,
|
24 |
"sliding_window": null,
|
25 |
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.36.2",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32005
|
30 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|bos|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,14 +1,12 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"pad_id": 32000,
|
9 |
-
"pad_type_id": 0,
|
10 |
-
"pad_token": "<|bos|>"
|
11 |
},
|
|
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
|
|
|
|
|
|
8 |
},
|
9 |
+
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -74,7 +74,10 @@
|
|
74 |
"legacy": true,
|
75 |
"max_length": 1536,
|
76 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
77 |
"pad_token": "<|bos|>",
|
|
|
|
|
78 |
"sp_model_kwargs": {},
|
79 |
"spaces_between_special_tokens": false,
|
80 |
"stride": 0,
|
|
|
74 |
"legacy": true,
|
75 |
"max_length": 1536,
|
76 |
"model_max_length": 1000000000000000019884624838656,
|
77 |
+
"pad_to_multiple_of": null,
|
78 |
"pad_token": "<|bos|>",
|
79 |
+
"pad_token_type_id": 0,
|
80 |
+
"padding_side": "right",
|
81 |
"sp_model_kwargs": {},
|
82 |
"spaces_between_special_tokens": false,
|
83 |
"stride": 0,
|