31 lines
716 B
JSON
31 lines
716 B
JSON
{
|
|
"_name_or_path": "m-a-p/OpenCodeInterpreter-DS-6.7B",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"bos_token_id": 32013,
|
|
"eos_token_id": 32021,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"max_position_embeddings": 16384,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": {
|
|
"factor": 4.0,
|
|
"type": "linear"
|
|
},
|
|
"rope_theta": 100000,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.34.1",
|
|
"use_cache": false,
|
|
"vocab_size": 32256
|
|
}
|