Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Inference Endpoints
Mahou-1.3-spark-7B / config.json
nbeerbower's picture
Upload Qwen2ForCausalLM
bf3c19e verified
raw
history blame contribute delete
733 Bytes
{
"_name_or_path": "arcee-ai/Arcee-Spark",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151644,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151646
}