Instructions to use fpadovani/wiki_w_30 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fpadovani/wiki_w_30 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="fpadovani/wiki_w_30")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("fpadovani/wiki_w_30") model = AutoModelForCausalLM.from_pretrained("fpadovani/wiki_w_30") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use fpadovani/wiki_w_30 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "fpadovani/wiki_w_30" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "fpadovani/wiki_w_30", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/fpadovani/wiki_w_30
- SGLang
How to use fpadovani/wiki_w_30 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 "fpadovani/wiki_w_30" \ --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": "fpadovani/wiki_w_30", "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 "fpadovani/wiki_w_30" \ --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": "fpadovani/wiki_w_30", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use fpadovani/wiki_w_30 with Docker Model Runner:
docker model run hf.co/fpadovani/wiki_w_30
Training in progress, step 1000, checkpoint
Browse files
checkpoint-1000/trainer_state.json
CHANGED
|
@@ -26,9 +26,9 @@
|
|
| 26 |
{
|
| 27 |
"epoch": 1.0,
|
| 28 |
"eval_loss": 6.196061611175537,
|
| 29 |
-
"eval_runtime":
|
| 30 |
-
"eval_samples_per_second":
|
| 31 |
-
"eval_steps_per_second":
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
|
@@ -41,9 +41,9 @@
|
|
| 41 |
{
|
| 42 |
"epoch": 2.0,
|
| 43 |
"eval_loss": 5.85089111328125,
|
| 44 |
-
"eval_runtime":
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second":
|
| 47 |
"step": 800
|
| 48 |
}
|
| 49 |
],
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 1.0,
|
| 28 |
"eval_loss": 6.196061611175537,
|
| 29 |
+
"eval_runtime": 15.8722,
|
| 30 |
+
"eval_samples_per_second": 1618.49,
|
| 31 |
+
"eval_steps_per_second": 6.363,
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
|
|
|
| 41 |
{
|
| 42 |
"epoch": 2.0,
|
| 43 |
"eval_loss": 5.85089111328125,
|
| 44 |
+
"eval_runtime": 15.8702,
|
| 45 |
+
"eval_samples_per_second": 1618.694,
|
| 46 |
+
"eval_steps_per_second": 6.364,
|
| 47 |
"step": 800
|
| 48 |
}
|
| 49 |
],
|
checkpoint-1000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bd8a847d4ccae62f28fa03470f7b388a6e051d0adb6cfd0ecec17d5b7bf3549
|
| 3 |
size 5905
|