63 lines
1.5 KiB
JSON
63 lines
1.5 KiB
JSON
{
|
|
"architectures": [
|
|
"GraniteForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attention_multiplier": 0.0078125,
|
|
"bos_token_id": 100257,
|
|
"embedding_multiplier": 12.0,
|
|
"eos_token_id": 100257,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.1,
|
|
"intermediate_size": 12800,
|
|
"logits_scaling": 16.0,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "granite",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 100256,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"input_activations": null,
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": false,
|
|
"group_size": 128,
|
|
"num_bits": 4,
|
|
"observer": "minmax",
|
|
"observer_kwargs": {},
|
|
"strategy": "group",
|
|
"symmetric": false,
|
|
"type": "int"
|
|
}
|
|
}
|
|
},
|
|
"format": "pack-quantized",
|
|
"global_compression_ratio": null,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed"
|
|
},
|
|
"residual_multiplier": 0.22,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.4",
|
|
"use_cache": true,
|
|
"vocab_size": 100352
|
|
} |