33 lines
806 B
JSON
33 lines
806 B
JSON
|
{
|
||
|
|
"_attn_implementation_autoset": false,
|
||
|
|
"_name_or_path": "CohereForAI/c4ai-command-r-v01",
|
||
|
|
"architectures": [
|
||
|
|
"CohereForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 5,
|
||
|
|
"eos_token_id": 255001,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 512,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 1408,
|
||
|
|
"layer_norm_eps": 1e-05,
|
||
|
|
"logit_scale": 0.0625,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"model_max_length": 131072,
|
||
|
|
"model_type": "cohere",
|
||
|
|
"num_attention_heads": 4,
|
||
|
|
"num_hidden_layers": 2,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 8000000.0,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.44.0",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_qk_norm": false,
|
||
|
|
"vocab_size": 256000
|
||
|
|
}
|