Helion-V1.5-XL / config.json
Trouter-Library's picture
Create config.json
d82b168 verified
raw
history blame
1.55 kB
{
"architectures": [
"HelionForCausalLM"
],
"model_type": "helion",
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"_name_or_path": "DeepXR/Helion-V1.5-XL",
"auto_map": {
"AutoConfig": "configuration_helion.HelionConfig",
"AutoModelForCausalLM": "modeling_helion.HelionForCausalLM"
},
"vocab_size": 100000,
"hidden_size": 6144,
"intermediate_size": 24576,
"num_hidden_layers": 48,
"num_attention_heads": 32,
"num_key_value_heads": 8,
"max_position_embeddings": 16384,
"rope_theta": 10000.0,
"rope_scaling": {
"type": "linear",
"factor": 2.0
},
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"use_cache": true,
"pad_token_id": 0,
"bos_token_id": 1,
"eos_token_id": 2,
"tie_word_embeddings": false,
"attention_bias": false,
"attention_dropout": 0.0,
"pretraining_tp": 1,
"use_flash_attention_2": true,
"use_sliding_window": false,
"sliding_window": null,
"quantization_config": {
"quant_method": "bitsandbytes",
"load_in_8bit": false,
"load_in_4bit": false,
"llm_int8_threshold": 6.0,
"llm_int8_has_fp16_weight": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_use_double_quant": true,
"bnb_4bit_quant_type": "nf4"
},
"generation_config": {
"max_length": 16384,
"max_new_tokens": 512,
"temperature": 0.7,
"top_p": 0.9,
"top_k": 50,
"repetition_penalty": 1.1,
"do_sample": true,
"num_beams": 1,
"early_stopping": false
}
}