RedPajama-INCITE-Base-3B-v1-wikipedia-8bit
/
flyte_4dtz63w
/local_flytekit
/5e5d536b4c662b7a5699a1dfbf8a9c95
/models--togethercomputer--RedPajama-INCITE-Base-3B-v1
/blobs
/7cb72eb7357994a07d5c54ffdeef99dec84e21ae
{ | |
"_name_or_path": "rp_3b_800b", | |
"architectures": [ | |
"GPTNeoXForCausalLM" | |
], | |
"bos_token_id": 0, | |
"eos_token_id": 0, | |
"hidden_act": "gelu", | |
"hidden_size": 2560, | |
"initializer_range": 0.02, | |
"intermediate_size": 10240, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 2048, | |
"model_type": "gpt_neox", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 32, | |
"rotary_emb_base": 10000, | |
"rotary_pct": 1.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.28.1", | |
"use_cache": true, | |
"use_parallel_residual": false, | |
"vocab_size": 50432 | |
} | |