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
| { | |
| "_sliding_window_pattern": 6, | |
| "architectures": [ | |
| "Gemma3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "dtype": "bfloat16", | |
| "eos_token_id": 106, | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 34, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 1024, | |
| "transformers_version": "4.56.1", | |
| "use_cache": false, | |
| "vocab_size": 262208 | |
| } | |