Instructions to use ethzanalytics/pythia-31m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ethzanalytics/pythia-31m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ethzanalytics/pythia-31m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ethzanalytics/pythia-31m") model = AutoModelForCausalLM.from_pretrained("ethzanalytics/pythia-31m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ethzanalytics/pythia-31m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ethzanalytics/pythia-31m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ethzanalytics/pythia-31m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ethzanalytics/pythia-31m
- SGLang
How to use ethzanalytics/pythia-31m with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ethzanalytics/pythia-31m" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ethzanalytics/pythia-31m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ethzanalytics/pythia-31m" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ethzanalytics/pythia-31m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ethzanalytics/pythia-31m with Docker Model Runner:
docker model run hf.co/ethzanalytics/pythia-31m
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,10 +4,52 @@ language:
|
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: EleutherAI/pythia-31m
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# pythia-31m (fp32)
|
| 10 |
|
| 11 |
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: EleutherAI/pythia-31m
|
| 7 |
+
datasets:
|
| 8 |
+
- EleutherAI/pile
|
| 9 |
+
tags:
|
| 10 |
+
- smol
|
| 11 |
---
|
| 12 |
|
| 13 |
# pythia-31m (fp32)
|
| 14 |
|
| 15 |
|
| 16 |
|
| 17 |
+
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.
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## config/info
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
```json
|
| 26 |
+
{
|
| 27 |
+
"_name_or_path": "EleutherAI/pythia-31m",
|
| 28 |
+
"architectures": [
|
| 29 |
+
"GPTNeoXForCausalLM"
|
| 30 |
+
],
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"bos_token_id": 0,
|
| 33 |
+
"classifier_dropout": 0.1,
|
| 34 |
+
"eos_token_id": 0,
|
| 35 |
+
"hidden_act": "gelu",
|
| 36 |
+
"hidden_dropout": 0.0,
|
| 37 |
+
"hidden_size": 256,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 1024,
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"max_position_embeddings": 2048,
|
| 42 |
+
"model_type": "gpt_neox",
|
| 43 |
+
"num_attention_heads": 8,
|
| 44 |
+
"num_hidden_layers": 6,
|
| 45 |
+
"rope_scaling": null,
|
| 46 |
+
"rotary_emb_base": 10000,
|
| 47 |
+
"rotary_pct": 0.25,
|
| 48 |
+
"tie_word_embeddings": false,
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.33.1",
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"use_parallel_residual": true,
|
| 53 |
+
"vocab_size": 50304
|
| 54 |
+
}
|
| 55 |
+
```
|