Instructions to use inclusionAI/Ling-3.1-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
Download config.json from inclusionAI/Ling-3.1-flash: direct link, hf CLI and curl.
- Browser
- Download file 6.64 kB
-
https://huggingface.co/inclusionAI/Ling-3.1-flash/resolve/main/config.json
- Command line
-
hf download hf://inclusionAI/Ling-3.1-flash/config.json
-
curl -L -o config.json https://huggingface.co/inclusionAI/Ling-3.1-flash/resolve/main/config.json
6.64 kB
| { | |
| "architectures": [ | |
| "BailingMoeV3ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_bailing_moe_v3.BailingMoeV3Config", | |
| "AutoModel": "modeling_bailing_moe_v3.BailingMoeV3Model", | |
| "AutoModelForCausalLM": "modeling_bailing_moe_v3.BailingMoeV3ForCausalLM" | |
| }, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 156895, | |
| "expert_swiglu_limit_list": [ | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10 | |
| ], | |
| "first_k_dense_replace": 4, | |
| "gated_attention_proj_granularity_type": "head_wise", | |
| "group_norm_size": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "kda_lower_bound": -5.0, | |
| "kda_safe_gate": true, | |
| "kv_lora_rank": 512, | |
| "layer_group_size": 8, | |
| "linear_silu": true, | |
| "max_position_embeddings": 262144, | |
| "max_window_layers": 20, | |
| "moe_intermediate_size": 1280, | |
| "moe_router_enable_expert_bias": true, | |
| "moe_shared_expert_intermediate_size": 1280, | |
| "mtp_loss_scaling_factor": 0, | |
| "mtp_use_kda": false, | |
| "n_group": 8, | |
| "no_kda_lora": true, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_experts": 512, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 72, | |
| "num_key_value_heads": 64, | |
| "num_kv_heads_for_linear_attn": 0, | |
| "num_nextn_predict_layers": 1, | |
| "num_shared_experts": 1, | |
| "output_dropout": 0.0, | |
| "output_router_logits": false, | |
| "pad_token_id": 156892, | |
| "partial_rotary_factor": 0.5, | |
| "q_lora_rank": 1536, | |
| "qk_head_dim": 192, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "quantization_config": { | |
| "activation_scheme": "dynamic", | |
| "fmt": "e4m3", | |
| "quant_method": "fp8", | |
| "modules_to_not_convert": [ | |
| "lm_head", | |
| "model.word_embeddings", | |
| "model.layers.0.attention.b_proj", | |
| "model.layers.1.attention.b_proj", | |
| "model.layers.2.attention.b_proj", | |
| "model.layers.3.attention.b_proj", | |
| "model.layers.4.attention.b_proj", | |
| "model.layers.5.attention.b_proj", | |
| "model.layers.6.attention.b_proj", | |
| "model.layers.8.attention.b_proj", | |
| "model.layers.9.attention.b_proj", | |
| "model.layers.10.attention.b_proj", | |
| "model.layers.11.attention.b_proj", | |
| "model.layers.12.attention.b_proj", | |
| "model.layers.13.attention.b_proj", | |
| "model.layers.14.attention.b_proj", | |
| "model.layers.16.attention.b_proj", | |
| "model.layers.17.attention.b_proj", | |
| "model.layers.18.attention.b_proj", | |
| "model.layers.19.attention.b_proj", | |
| "model.layers.20.attention.b_proj", | |
| "model.layers.21.attention.b_proj", | |
| "model.layers.22.attention.b_proj", | |
| "model.layers.24.attention.b_proj", | |
| "model.layers.25.attention.b_proj", | |
| "model.layers.26.attention.b_proj", | |
| "model.layers.27.attention.b_proj", | |
| "model.layers.28.attention.b_proj", | |
| "model.layers.29.attention.b_proj", | |
| "model.layers.30.attention.b_proj", | |
| "model.layers.32.attention.b_proj", | |
| "model.layers.33.attention.b_proj", | |
| "model.layers.34.attention.b_proj", | |
| "model.layers.35.attention.b_proj", | |
| "model.layers.36.attention.b_proj", | |
| "model.layers.37.attention.b_proj", | |
| "model.layers.38.attention.b_proj", | |
| "model.layers.40.attention.b_proj", | |
| "model.layers.41.attention.b_proj", | |
| "model.layers.42.attention.b_proj", | |
| "model.layers.43.attention.b_proj", | |
| "model.layers.44.attention.b_proj", | |
| "model.layers.45.attention.b_proj", | |
| "model.layers.46.attention.b_proj", | |
| "model.layers.48.attention.b_proj", | |
| "model.layers.49.attention.b_proj", | |
| "model.layers.50.attention.b_proj", | |
| "model.layers.51.attention.b_proj", | |
| "model.layers.52.attention.b_proj", | |
| "model.layers.53.attention.b_proj", | |
| "model.layers.54.attention.b_proj", | |
| "model.layers.56.attention.b_proj", | |
| "model.layers.57.attention.b_proj", | |
| "model.layers.58.attention.b_proj", | |
| "model.layers.59.attention.b_proj", | |
| "model.layers.60.attention.b_proj", | |
| "model.layers.61.attention.b_proj", | |
| "model.layers.62.attention.b_proj", | |
| "model.layers.64.attention.b_proj", | |
| "model.layers.65.attention.b_proj", | |
| "model.layers.66.attention.b_proj", | |
| "model.layers.67.attention.b_proj", | |
| "model.layers.68.attention.b_proj", | |
| "model.layers.69.attention.b_proj", | |
| "model.layers.70.attention.b_proj", | |
| "model.layers.7.attention.g_proj", | |
| "model.layers.15.attention.g_proj", | |
| "model.layers.23.attention.g_proj", | |
| "model.layers.31.attention.g_proj", | |
| "model.layers.39.attention.g_proj", | |
| "model.layers.47.attention.g_proj", | |
| "model.layers.55.attention.g_proj", | |
| "model.layers.63.attention.g_proj", | |
| "model.layers.71.attention.g_proj", | |
| "model.layers.72.eh_proj" | |
| ], | |
| "weight_block_size": [ | |
| 128, | |
| 128 | |
| ] | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": null, | |
| "rope_theta": 6000000, | |
| "rotary_dim": 64, | |
| "routed_scaling_factor": 2.5, | |
| "router_dtype": "fp32", | |
| "scale_router_input": false, | |
| "score_function": "sigmoid", | |
| "scoring_func": "sigmoid", | |
| "seq_aux": true, | |
| "share_expert_swiglu_limit_list": [ | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 0, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10, | |
| 10 | |
| ], | |
| "short_conv_kernel_size": 4, | |
| "tie_word_embeddings": false, | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "transformers_version": "4.45.0", | |
| "up_proj_norm": false, | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_kda_lora": false, | |
| "use_mla_nope": false, | |
| "use_nGPT": false, | |
| "use_qk_norm": true, | |
| "use_qkv_bias": false, | |
| "v_head_dim": 128, | |
| "value_norm": false, | |
| "vocab_size": 157184, | |
| "model_type": "bailing_hybrid", | |
| "torch_dtype": "bfloat16" | |
| } | |