Instructions to use AtBeginDocument/II-Medical-8B-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AtBeginDocument/II-Medical-8B-oQ4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir II-Medical-8B-oQ4 AtBeginDocument/II-Medical-8B-oQ4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "lm_head": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "lm_head": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.16.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.17.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.18.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.23.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.25.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.28.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.32.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |
| } |