Feature Extraction
Transformers
Safetensors
qwen3
fp8
compressed-tensors
llm-compressor
vllm
embedding
text-embeddings-inference
Instructions to use DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic") model = AutoModel.from_pretrained("DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Qwen3Model" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "format": "float-quantized", | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "scale_dtype": null, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "float", | |
| "zp_dtype": null | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "memoryless_minmax", | |
| "observer_kwargs": {}, | |
| "scale_dtype": null, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "float", | |
| "zp_dtype": null | |
| } | |
| } | |
| }, | |
| "format": "float-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": {}, | |
| "transform_config": {}, | |
| "version": "0.17.1" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.10.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151665 | |
| } |