Text Classification
Transformers
Safetensors
English
Chinese
qwen3_5_moe_text
text-generation
decision-model
web-agent
browser-agent
typed-decisions
structured-output
one-pass
mixture-of-experts
Instructions to use Lexmount/WebJev-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lexmount/WebJev-35B-A3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Lexmount/WebJev-35B-A3B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lexmount/WebJev-35B-A3B") model = AutoModelForCausalLM.from_pretrained("Lexmount/WebJev-35B-A3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Lexmount/WebJev-35B-A3B: direct link, hf CLI and curl.
- Browser
- Download file 2.38 kB
-
https://huggingface.co/Lexmount/WebJev-35B-A3B/resolve/main/config.json
- Command line
-
hf download hf://Lexmount/WebJev-35B-A3B/config.json
-
curl -L -o config.json https://huggingface.co/Lexmount/WebJev-35B-A3B/resolve/main/config.json
2.38 kB
| { | |
| "architectures": [ | |
| "Qwen3_5MoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "experts_implementation": "grouped_mm", | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_moe_text", | |
| "moe_intermediate_size": 512, | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 16, | |
| "num_experts": 256, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "output_router_logits": false, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 512, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.15.1", | |
| "use_cache": false, | |
| "vocab_size": 248320 | |
| } | |