File size: 1,444 Bytes
adfa52f | 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 | {
"_entry_class": "SingleModelCacheEntry",
"_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
"_task": "text-generation",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 131072,
"max_window_layers": 21,
"model_type": "qwen2",
"neuron": {
"_serialized_key": "HloNeuronConfig",
"all_reduce_dtype": null,
"allow_flash_attention": true,
"attention_layout": "HSB",
"attn_output_transposed": false,
"auto_cast_type": "bf16",
"batch_size": 1,
"checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
"checkpoint_revision": "ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562",
"collectives_layout": "HSB",
"continuous_batching": false,
"fuse_qkv": false,
"group_query_attention": "shard-over-heads",
"log_softmax_scores": false,
"neuronxcc_version": "2.17.194.0+d312836f",
"optimum_neuron_version": "0.2.0.dev7",
"output_all_logits": false,
"sequence_length": 4096,
"tp_degree": 2
},
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"sliding_window": 4096,
"tie_word_embeddings": false,
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 151936
} |