demo-model_sandeep / config.json
quarkx33's picture
Upload model
43ce37d
raw
history blame contribute delete
842 Bytes
{
"_name_or_path": "EleutherAI/pythia-1b-deduped",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_probs_dropout_prob": 0.0,
"bos_token_id": 0,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 8,
"num_hidden_layers": 16,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50304
}