File size: 1,252 Bytes
cd7afcd 94e5aad cd7afcd 8a46fee cd7afcd 8a46fee cd7afcd 8a46fee cd7afcd | 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 51 | {
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"quantization_config": {
"config_groups": {},
"format": "dense",
"global_compression_ratio": null,
"ignore": [],
"kv_cache_scheme": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "tensor",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.18.1.a20260910"
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 32000
} |