Instructions to use yanolja/YanoljaNEXT-Rosetta-4B-2511 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yanolja/YanoljaNEXT-Rosetta-4B-2511 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="yanolja/YanoljaNEXT-Rosetta-4B-2511")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("yanolja/YanoljaNEXT-Rosetta-4B-2511") model = AutoModelForCausalLM.from_pretrained("yanolja/YanoljaNEXT-Rosetta-4B-2511", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| {%- set system_msg = messages | selectattr('role', 'eq', 'system') | list | first | default(none) -%} | |
| {%- set last_user = messages | selectattr('role', 'eq', 'user') | list | last | default(none) -%} | |
| {%- set last_assistant = messages | selectattr('role', 'eq', 'assistant') | list | last | default(none) -%} | |
| {{- bos_token -}} | |
| {%- if system_msg -%} | |
| <start_of_turn>instruction{{ '\n' }} | |
| {{- system_msg['content'] | trim -}}<end_of_turn>{{ '\n' }} | |
| {%- endif -%} | |
| {%- if last_user -%} | |
| <start_of_turn>source{{ '\n' }} | |
| {{- last_user['content'] | trim -}}<end_of_turn>{{ '\n' }} | |
| {%- endif -%} | |
| {%- if add_generation_prompt -%} | |
| <start_of_turn>translation{{ '\n' }} | |
| {%- elif last_assistant -%} | |
| <start_of_turn>translation{{ '\n' }} | |
| {{- last_assistant['content'] | trim -}}<end_of_turn>{{ '\n' }} | |
| {%- endif -%} |