Instructions to use mpasila/Viking-SlimSonnet-v1-LoRA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mpasila/Viking-SlimSonnet-v1-LoRA-7B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LumiOpen/Viking-7B") model = PeftModel.from_pretrained(base_model, "mpasila/Viking-SlimSonnet-v1-LoRA-7B") - Transformers
How to use mpasila/Viking-SlimSonnet-v1-LoRA-7B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mpasila/Viking-SlimSonnet-v1-LoRA-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use mpasila/Viking-SlimSonnet-v1-LoRA-7B 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 mpasila/Viking-SlimSonnet-v1-LoRA-7B 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 mpasila/Viking-SlimSonnet-v1-LoRA-7B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for mpasila/Viking-SlimSonnet-v1-LoRA-7B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="mpasila/Viking-SlimSonnet-v1-LoRA-7B", max_seq_length=2048, )
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -195,7 +195,7 @@
|
|
| 195 |
}
|
| 196 |
},
|
| 197 |
"bos_token": "<s>",
|
| 198 |
-
"chat_template": "{%
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 195 |
}
|
| 196 |
},
|
| 197 |
"bos_token": "<s>",
|
| 198 |
+
"chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for message in messages %}\n {%- if message['role'] == 'system' -%}\n {{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}\n {%- else -%}\n {%- if message['role'] == 'user' -%}\n {{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}\n {%- else -%}\n {{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{-'<|im_start|>assistant\n'-}}\n{%- endif -%}",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"model_max_length": 1000000000000000019884624838656,
|