Instructions to use saberbx/phiSentryV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saberbx/phiSentryV2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("saberbx/phiSentryV2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use saberbx/phiSentryV2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for saberbx/phiSentryV2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for saberbx/phiSentryV2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for saberbx/phiSentryV2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="saberbx/phiSentryV2", max_seq_length=2048, )
Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- special_tokens_map.json +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"content": "<|placeholder6|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
-
"rstrip":
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
|
|
|
| 17 |
"content": "<|placeholder6|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
+
"rstrip": true,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
tokenizer.json
CHANGED
|
@@ -116,7 +116,7 @@
|
|
| 116 |
"content": "<|placeholder6|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
-
"rstrip":
|
| 120 |
"normalized": false,
|
| 121 |
"special": true
|
| 122 |
},
|
|
|
|
| 116 |
"content": "<|placeholder6|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
+
"rstrip": true,
|
| 120 |
"normalized": false,
|
| 121 |
"special": true
|
| 122 |
},
|
tokenizer_config.json
CHANGED
|
@@ -103,7 +103,7 @@
|
|
| 103 |
"content": "<|placeholder6|>",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": false,
|
| 106 |
-
"rstrip":
|
| 107 |
"single_word": false,
|
| 108 |
"special": true
|
| 109 |
},
|
|
@@ -122,7 +122,7 @@
|
|
| 122 |
"extra_special_tokens": {},
|
| 123 |
"legacy": false,
|
| 124 |
"max_length": 1024,
|
| 125 |
-
"model_max_length":
|
| 126 |
"pad_token": "<|placeholder6|>",
|
| 127 |
"padding_side": "right",
|
| 128 |
"sp_model_kwargs": {},
|
|
|
|
| 103 |
"content": "<|placeholder6|>",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
"single_word": false,
|
| 108 |
"special": true
|
| 109 |
},
|
|
|
|
| 122 |
"extra_special_tokens": {},
|
| 123 |
"legacy": false,
|
| 124 |
"max_length": 1024,
|
| 125 |
+
"model_max_length": 131072,
|
| 126 |
"pad_token": "<|placeholder6|>",
|
| 127 |
"padding_side": "right",
|
| 128 |
"sp_model_kwargs": {},
|