|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
base_model: EleutherAI/pythia-31m |
|
datasets: |
|
- EleutherAI/pile |
|
tags: |
|
- smol |
|
--- |
|
|
|
# pythia-31m (fp32) |
|
|
|
|
|
|
|
This is [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) but saved explicitly in fp32 - see safetensors params. It is smaller than the other 'official' checkpoints included in the Pythia study. |
|
|
|
|
|
|
|
|
|
## config/info |
|
|
|
|
|
```json |
|
{ |
|
"_name_or_path": "EleutherAI/pythia-31m", |
|
"architectures": [ |
|
"GPTNeoXForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 0, |
|
"classifier_dropout": 0.1, |
|
"eos_token_id": 0, |
|
"hidden_act": "gelu", |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 256, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 1024, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "gpt_neox", |
|
"num_attention_heads": 8, |
|
"num_hidden_layers": 6, |
|
"rope_scaling": null, |
|
"rotary_emb_base": 10000, |
|
"rotary_pct": 0.25, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.33.1", |
|
"use_cache": true, |
|
"use_parallel_residual": true, |
|
"vocab_size": 50304 |
|
} |
|
``` |
|
|
