dacorvo's picture
dacorvo HF Staff
Synchronizing local compiler cache.
c3c1a4a verified
{
"_entry_class": "SingleModelCacheEntry",
"_model_id": "Qwen/Qwen2.5-32B-Instruct",
"_task": "text-generation",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"neuron": {
"_serialized_key": "NxDNeuronConfig",
"async_mode": false,
"attn_kernel_enabled": false,
"batch_size": 8,
"capacity_factor": null,
"cc_pipeline_tiling_factor": 2,
"checkpoint_id": "Qwen/Qwen2.5-32B-Instruct",
"checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
"continuous_batching": true,
"enable_bucketing": false,
"ep_degree": 1,
"flash_decoding_enabled": false,
"fused_qkv": false,
"glu_mlp": true,
"is_chunked_prefill": false,
"local_ranks_size": 8,
"logical_nc_config": 1,
"max_batch_size": 8,
"max_context_length": 4096,
"max_topk": 256,
"mlp_kernel_enabled": false,
"mlp_kernel_fuse_residual_add": false,
"n_active_tokens": 4096,
"neuronxcc_version": "2.17.194.0+d312836f",
"num_cores_per_group": 1,
"on_device_sampling": true,
"optimum_neuron_version": "0.3.0.dev3",
"output_logits": false,
"padding_side": "right",
"pp_degree": 1,
"qk_layernorm": false,
"qkv_kernel_enabled": false,
"rpl_reduce_dtype": "bfloat16",
"sequence_length": 4096,
"sequence_parallel_enabled": false,
"speculation_length": 0,
"start_rank_id": 0,
"target": null,
"torch_dtype": "bfloat16",
"tp_degree": 8,
"vocab_parallel": false
},
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}