Llemma-7B-32K-MathMix / config.json
AlexChvl's picture
adding model and tokenizer
433c566
raw
history blame contribute delete
793 Bytes
{
"_name_or_path": "awettig_models_long/ft_EleutherAI--llemma_7b_bsz512_lr2e-5_epochs1_warmup0.1_datasetopen-web-math-llama32k-equiloglengths-small_theta1000000",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 32016
}