stablelm-4e1t-2b-v0.1 / config.json
pszemraj's picture
reset use_cache
e502a49 verified
{
"_name_or_path": "pszemraj/stablelm-3b-4e1t-prune10",
"architectures": [
"StableLmForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_dropout": 0.0,
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4096,
"model_type": "stablelm",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.25,
"qk_layernorm": false,
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"use_parallel_residual": false,
"use_qkv_bias": false,
"vocab_size": 50304
}