Instructions to use keras/qwen2.5_coder_instruct_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/qwen2.5_coder_instruct_7b with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://keras/qwen2.5_coder_instruct_7b", dtype="bfloat16") causal_lm.compile(sampler="greedy") # (optional) specify a sampler # Generate text causal_lm.generate("Keras: deep learning for", max_length=64)import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/qwen2.5_coder_instruct_7b") - Keras
How to use keras/qwen2.5_coder_instruct_7b with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/qwen2.5_coder_instruct_7b") - Notebooks
- Google Colab
- Kaggle
| { | |
| "module": "keras_hub.src.models.qwen.qwen_tokenizer", | |
| "class_name": "QwenTokenizer", | |
| "config": { | |
| "name": "qwen_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "sequence_length": null, | |
| "add_prefix_space": false, | |
| "unsplittable_tokens": [ | |
| "<|file_sep|>", | |
| "<|vision_start|>", | |
| "<|quad_start|>", | |
| "<|object_ref_start|>", | |
| "<|fim_pad|>", | |
| "<|fim_suffix|>", | |
| "<|image_pad|>", | |
| "<|fim_middle|>", | |
| "</tool_call>", | |
| "<|box_end|>", | |
| "<|object_ref_end|>", | |
| "<|quad_end|>", | |
| "<|vision_pad|>", | |
| "<|repo_name|>", | |
| "<|box_start|>", | |
| "<|fim_prefix|>", | |
| "<|vision_end|>", | |
| "<tool_call>", | |
| "<|im_end|>", | |
| "<|endoftext|>", | |
| "<|im_start|>", | |
| "<|video_pad|>" | |
| ] | |
| }, | |
| "registered_name": "keras_hub>QwenTokenizer" | |
| } |