JunHowie's picture
Upload folder using huggingface_hub
afb6654 verified
raw
history blame
1.28 kB
{
"name_or_path": "tclf90/Qwen3-235B-A22B-GPTQ-Int8",
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 40960,
"max_window_layers": 94,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 1536,
"norm_topk_prob": true,
"num_attention_heads": 64,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 94,
"num_key_value_heads": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936,
"quantization_config": {
"quant_method": "gptq",
"bits": 8,
"group_size": 128,
"sym": true,
"desc_act": false,
"block_name_to_quantize": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null
}
}