dacorvo's picture
dacorvo HF Staff
Synchronizing local compiler cache.
913e738 verified
raw
history blame
1.41 kB
{
"_entry_class": "SingleModelCacheEntry",
"_model_id": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"_task": "text-generation",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"neuron": {
"_serialized_key": "HloNeuronConfig",
"all_reduce_dtype": null,
"allow_flash_attention": true,
"attention_layout": "BSH",
"attn_output_transposed": false,
"auto_cast_type": "bf16",
"batch_size": 1,
"checkpoint_id": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"checkpoint_revision": "fe8a4ea1ffedaf415f4da2f062534de366a451e6",
"collectives_layout": "HSB",
"continuous_batching": false,
"fuse_qkv": true,
"group_query_attention": "shard-over-heads",
"log_softmax_scores": false,
"neuronxcc_version": "2.17.194.0+d312836f",
"optimum_neuron_version": "0.2.0.dev5",
"output_all_logits": false,
"sequence_length": 2048,
"tp_degree": 2
},
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 32000
}