Orion
add: model files
29c10d8
raw
history blame contribute delete
993 Bytes
{
"_name_or_path": "mistral-community/Codestral-22B-v0.1",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 6144,
"initializer_range": 0.02,
"intermediate_size": 16384,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 48,
"num_hidden_layers": 56,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.0.dev0",
"use_cache": true,
"vocab_size": 32768,
"quantization_config": {
"quant_method": "exl2",
"version": "0.2.2",
"bits": 4.65,
"head_bits": 8,
"calibration": {
"rows": 100,
"length": 2048,
"dataset": "train-00000-of-01126.parquet"
}
}
}