Instructions to use dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX --local-dir Hy-MT2-30B-A3B-oQ8-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX: direct link, hf CLI and curl.
- Browser
- Download file 1.3 kB
-
https://huggingface.co/dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/resolve/main/config.json
- Command line
-
hf download hf://dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/config.json
-
curl -L -o config.json https://huggingface.co/dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/resolve/main/config.json
1.3 kB
| { | |
| "architectures": [ | |
| "HYV3ForCausalLM" | |
| ], | |
| "attn_impl": "eager", | |
| "bos_token_id": 120000, | |
| "enable_attention_fp32_softmax": false, | |
| "enable_lm_head_fp32": true, | |
| "enable_moe_fp32_combine": false, | |
| "eod_token_id": 120026, | |
| "eos_token_id": 120025, | |
| "expert_hidden_dim": 768, | |
| "moe_intermediate_size": 768, | |
| "first_k_dense_replace": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.006, | |
| "intermediate_size": 6912, | |
| "max_position_embeddings": 262144, | |
| "model_type": "hy_v3", | |
| "moe_router_enable_expert_bias": true, | |
| "moe_router_use_sigmoid": true, | |
| "num_attention_heads": 32, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 4, | |
| "num_shared_experts": 1, | |
| "output_router_logits": true, | |
| "pad_token_id": 120002, | |
| "qk_norm": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 11158840.0, | |
| "route_norm": true, | |
| "router_scaling_factor": 2.826, | |
| "sep_token_id": 120007, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "use_grouped_mm": false, | |
| "vocab_size": 120832, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| } |