Transformers
GGUF
English
Chinese
chat-template
reasoning
cot
protium
solstice-ai
objective-gated
zero-waste
dynamic-reasoning
ollama
llama.cpp
vllm
Instructions to use Solstice-AI/Protium-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Solstice-AI/Protium-1.0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Solstice-AI/Protium-1.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
feat: update regular_mistral.jinja with v3.0 soft-spectrum and regular mode
Browse files
templates/regular_mistral.jinja
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token -}}
|
| 2 |
+
{%- for message in messages -%}
|
| 3 |
+
{%- if message['role'] == 'user' -%}
|
| 4 |
+
{{- '[INST] ' + message['content'] | trim + ' [/INST]' -}}
|
| 5 |
+
{%- elif message['role'] == 'assistant' -%}
|
| 6 |
+
{{- ' ' + message['content'] | trim + eos_token -}}
|
| 7 |
+
{%- elif message['role'] == 'system' -%}
|
| 8 |
+
{{- '[INST] ' + message['content'] | trim + ' [/INST]' -}}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- endfor -%}
|