Instructions to use fromthesky/PLDR-LLM-v51-110M-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fromthesky/PLDR-LLM-v51-110M-4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="fromthesky/PLDR-LLM-v51-110M-4", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("fromthesky/PLDR-LLM-v51-110M-4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fromthesky/PLDR-LLM-v51-110M-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fromthesky/PLDR-LLM-v51-110M-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fromthesky/PLDR-LLM-v51-110M-4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fromthesky/PLDR-LLM-v51-110M-4

SGLang

How to use fromthesky/PLDR-LLM-v51-110M-4 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 "fromthesky/PLDR-LLM-v51-110M-4" \
    --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": "fromthesky/PLDR-LLM-v51-110M-4",
		"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 "fromthesky/PLDR-LLM-v51-110M-4" \
        --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": "fromthesky/PLDR-LLM-v51-110M-4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fromthesky/PLDR-LLM-v51-110M-4 with Docker Model Runner:
```
docker model run hf.co/fromthesky/PLDR-LLM-v51-110M-4
```

fromthesky commited on Dec 21, 2025

Commit

e095aa7

1 Parent(s): d6b7497

Updated readme.

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -45,18 +45,18 @@ Using `pipeline`:
 ```python
 from transformers import pipeline
-pipeline = pipeline(
-    task="text-generation",
-    model="fromthesky/PLDR-LLM-v51-110M-4",
-    device="cuda", # or "cpu"
-    trust_remote_code=True
-)
 prompt="The quick brown fox jumps over the lazy dog."
-output=pipeline(prompt, top_p=0.6, top_k=0, temperature=1, do_sample=True,
-                tokenizer_encode_kwargs={"add_special_tokens":False},
-                use_cache=True, max_new_tokens=100)
 print(output[0]["generated_text"])
 ```

 ```python
 from transformers import pipeline
+text_generator = pipeline(
+                          task="text-generation",
+                          model="fromthesky/PLDR-LLM-v51-110M-4",
+                          device="cuda", # or "cpu"
+                          trust_remote_code=True
+                         )
 prompt="The quick brown fox jumps over the lazy dog."
+output=text_generator(prompt, top_p=0.6, top_k=0, temperature=1, do_sample=True,
+                      tokenizer_encode_kwargs={"add_special_tokens":False},
+                      use_cache=True, max_new_tokens=100)
 print(output[0]["generated_text"])
 ```