Instructions to use edbeeching/pythia-160M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use edbeeching/pythia-160M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="edbeeching/pythia-160M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("edbeeching/pythia-160M") model = AutoModelForCausalLM.from_pretrained("edbeeching/pythia-160M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use edbeeching/pythia-160M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "edbeeching/pythia-160M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "edbeeching/pythia-160M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/edbeeching/pythia-160M
- SGLang
How to use edbeeching/pythia-160M 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 "edbeeching/pythia-160M" \ --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": "edbeeching/pythia-160M", "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 "edbeeching/pythia-160M" \ --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": "edbeeching/pythia-160M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use edbeeching/pythia-160M with Docker Model Runner:
docker model run hf.co/edbeeching/pythia-160M
Commit ·
739ae19
1
Parent(s): 3337edf
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +31 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.494479894366823,
|
| 4 |
+
"train_runtime": 494.2881,
|
| 5 |
+
"train_samples": 7031,
|
| 6 |
+
"train_samples_per_second": 14.224,
|
| 7 |
+
"train_steps_per_second": 1.778
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.494479894366823,
|
| 4 |
+
"train_runtime": 494.2881,
|
| 5 |
+
"train_samples": 7031,
|
| 6 |
+
"train_samples_per_second": 14.224,
|
| 7 |
+
"train_steps_per_second": 1.778
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 879,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.57,
|
| 12 |
+
"learning_rate": 2.1558589306029582e-05,
|
| 13 |
+
"loss": 3.5348,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"step": 879,
|
| 19 |
+
"total_flos": 5343195203371008.0,
|
| 20 |
+
"train_loss": 3.494479894366823,
|
| 21 |
+
"train_runtime": 494.2881,
|
| 22 |
+
"train_samples_per_second": 14.224,
|
| 23 |
+
"train_steps_per_second": 1.778
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 879,
|
| 27 |
+
"num_train_epochs": 1,
|
| 28 |
+
"total_flos": 5343195203371008.0,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|