Feature Extraction
MLX
Safetensors
qwen2
embeddings
sentence-similarity
quantization
omlx
q6
6-bit
custom_code
Instructions to use TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gte-Qwen2-1.5B-instruct-MLX-Q6 TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "schema_version": 1, | |
| "published_repository": "TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q6", | |
| "family": "gte-Qwen2-1.5B-instruct", | |
| "variant": "Q6", | |
| "upstream_repository": "Alibaba-NLP/gte-Qwen2-1.5B-instruct", | |
| "upstream_revision": "a9af15a6372d7d6b25e9fb07c2ccb9e1fe645644", | |
| "upstream_revision_evidence": "upstream revision verified at publication time; historical local snapshot metadata was not retained", | |
| "direct_parent": "TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16", | |
| "direct_parent_weight_hashes": [ | |
| { | |
| "file": "model.safetensors", | |
| "sha256": "9e9da58bd1371c47a08bc82f58bd29d33a6831094372dd717d68148f061dd11a", | |
| "bytes": 3552432732 | |
| } | |
| ], | |
| "conversion": { | |
| "method": "Q uniform affine quantization", | |
| "nominal_bits": 6, | |
| "group_size": 64, | |
| "importance_matrix": false, | |
| "importance_matrix_samples": null, | |
| "importance_matrix_sequence_length": null, | |
| "stack": { | |
| "omlx": "0.5.3", | |
| "mlx_lm": "0.31.3", | |
| "mlx": "0.32.0" | |
| }, | |
| "lossy_parent": false | |
| }, | |
| "weight_files": [ | |
| { | |
| "file": "model.safetensors", | |
| "sha256": "2da02d9f35059fd21ef065dda0c77b7f5fabda4bed096fb83d7607ec519ee7a7", | |
| "bytes": 1443414458 | |
| } | |
| ], | |
| "evaluation": { | |
| "pair_count": 24, | |
| "top1": 1.0, | |
| "recall_at_5": 1.0, | |
| "mrr": 1.0, | |
| "mean_aligned_embedding_cosine_vs_bf16": 0.9977855682373047, | |
| "minimum_aligned_embedding_cosine_vs_bf16": 0.9961316585540771, | |
| "score_rmse_vs_bf16": 0.004666702821850777, | |
| "queries_with_rank_change": 0, | |
| "gate_passed": true, | |
| "gate_criteria": { | |
| "top1_delta_min": 0.0, | |
| "recall_at_5_delta_min": 0.0, | |
| "mrr_delta_min": -0.01, | |
| "minimum_aligned_embedding_cosine_min": 0.99, | |
| "queries_with_rank_change_max": 2 | |
| } | |
| }, | |
| "collection": "https://huggingface.co/collections/TiGa-RCE/mlx-embedding-quantization-matrix-q-oq-oqe-at-4-6-8-bit-6a68d11afb238d4fe967d70b" | |
| } | |