90 lines
2.2 KiB
JSON
90 lines
2.2 KiB
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 2,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 960,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2560,
|
|
"is_llama_config": true,
|
|
"max_position_embeddings": 8192,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 15,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 5,
|
|
"pad_token_id": 2,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"format": "nvfp4-pack-quantized",
|
|
"input_activations": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": "local",
|
|
"group_size": 16,
|
|
"num_bits": 4,
|
|
"observer": "static_minmax",
|
|
"observer_kwargs": {},
|
|
"scale_dtype": "torch.float8_e4m3fn",
|
|
"strategy": "tensor_group",
|
|
"symmetric": true,
|
|
"type": "float",
|
|
"zp_dtype": null
|
|
},
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": false,
|
|
"group_size": 16,
|
|
"num_bits": 4,
|
|
"observer": "memoryless_minmax",
|
|
"observer_kwargs": {},
|
|
"scale_dtype": "torch.float8_e4m3fn",
|
|
"strategy": "tensor_group",
|
|
"symmetric": true,
|
|
"type": "float",
|
|
"zp_dtype": null
|
|
}
|
|
}
|
|
},
|
|
"format": "nvfp4-pack-quantized",
|
|
"global_compression_ratio": null,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed",
|
|
"sparsity_config": {},
|
|
"transform_config": {},
|
|
"version": "0.17.1"
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_interleaved": false,
|
|
"rope_parameters": {
|
|
"rope_theta": 100000,
|
|
"rope_type": "default"
|
|
},
|
|
"tie_word_embeddings": true,
|
|
"transformers.js_config": {
|
|
"kv_cache_dtype": {
|
|
"fp16": "float16",
|
|
"q4f16": "float16"
|
|
}
|
|
},
|
|
"transformers_version": "5.10.1",
|
|
"use_cache": true,
|
|
"vocab_size": 49152
|
|
} |