Text Generation
Transformers
PyTorch
Japanese
English
qwen2
conversational
text-generation-inference
Inference Endpoints
Kendamarron's picture
Upload folder using huggingface_hub
2e2cf31 verified
raw
history blame
722 Bytes
{
"_name_or_path": "Kendamarron/tokara-0.5B-v0.1-2.5ksteps",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}