Text Classification
Transformers
Safetensors
English
qwen3_5_text
text-generation
decision-model
typed-decisions
one-pass
option-probabilities
Instructions to use thegovind/blink-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thegovind/blink-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="thegovind/blink-4b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thegovind/blink-4b") model = AutoModelForCausalLM.from_pretrained("thegovind/blink-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 369 Bytes
400f1f6 | 1 2 3 4 5 6 7 8 9 10 | """Map merged text weights to their matching vision-language parent."""
def text_to_parent(key: str) -> str:
if key == "lm_head.weight" or key.startswith("model.language_model."):
return key
if key.startswith("model."):
return "model.language_model." + key[len("model."):]
raise ValueError(f"unexpected key in the text checkpoint: {key}")
|