omega-platy / config.json
winglian's picture
Training in progress, step 62
558ff67
raw
history blame contribute delete
No virus
1.34 kB
{
"_name_or_path": "winglian/omega-3b",
"activation_function": "gelu_new",
"architecture": {
"block_cls": "parallel",
"mixer": {},
"mlp": {
"mlp_cls": "mlp"
}
},
"architectures": [
"MixFormerSequentialForCausalLM"
],
"auto_map": {
"AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
"AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
},
"embd_layer": "default",
"embd_pdrop": 0.0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "mixformer-sequential",
"n_embd": 2048,
"n_head": 32,
"n_inner": null,
"n_layer": 48,
"n_positions": 2048,
"phyagi_version": "0.0.4.dev",
"quantization_config": {
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"resid_pdrop": 0.0,
"rotary_dim": 32,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": false,
"vocab_size": 50304
}