Text Generation
Transformers
Safetensors
Finnish
llama
finnish
conversational
text-generation-inference
Ahma-3B / config.json
aapot
Add 2-stage 1060k step model
ce7ff6d
raw
history blame
662 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.0.dev0",
"use_cache": true,
"vocab_size": 64256
}