Instructions to use N8Programs/lil-bard-checkpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use N8Programs/lil-bard-checkpts with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("N8Programs/lil-bard-checkpts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 881 Bytes
5f1f69f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | {
"architectures": [
"Qwen3MoeForCausalLM"
],
"model_type": "qwen3_moe",
"vocab_size": 8192,
"hidden_size": 512,
"num_hidden_layers": 16,
"intermediate_size": 1536,
"num_attention_heads": 4,
"num_key_value_heads": 2,
"head_dim": 128,
"hidden_act": "silu",
"rms_norm_eps": 1e-06,
"max_position_embeddings": 32768,
"rope_theta": 1000000.0,
"rope_scaling": null,
"attention_bias": false,
"attention_dropout": 0.0,
"tie_word_embeddings": false,
"use_cache": true,
"bos_token_id": 8190,
"eos_token_id": 0,
"pad_token_id": 8191,
"torch_dtype": "float32",
"decoder_sparse_step": 1,
"moe_intermediate_size": 768,
"num_experts": 8,
"num_experts_per_tok": 2,
"norm_topk_prob": true,
"output_router_logits": false,
"router_aux_loss_coef": 0.001,
"mlp_only_layers": [],
"use_sliding_window": false,
"sliding_window": null
} |