File size: 1,267 Bytes
79397d9 f79f272 79397d9 |
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 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
{
"name_or_path": "tclf90/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8",
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_dropout": 0.0,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5472,
"max_position_embeddings": 262144,
"max_window_layers": 28,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"output_router_logits": false,
"qkv_bias": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000000,
"router_aux_loss_coef": 0.0,
"shared_expert_intermediate_size": 0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.52.3",
"use_cache": true,
"use_qk_norm": true,
"use_sliding_window": false,
"vocab_size": 151936,
"quantization_config": {
"quant_method": "gptq",
"bits": 8,
"group_size": 128,
"sym": true,
"desc_act": false,
"dynamic": {
"-:model[.]layers[.]\\d+[.]mlp.gate*": {}
}
}
} |