Instructions to use distributed/optimized-gpt2-1b-vtestnet-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distributed/optimized-gpt2-1b-vtestnet-v2 with Transformers:

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

pipe = pipeline("text-generation", model="distributed/optimized-gpt2-1b-vtestnet-v2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("distributed/optimized-gpt2-1b-vtestnet-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use distributed/optimized-gpt2-1b-vtestnet-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "distributed/optimized-gpt2-1b-vtestnet-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "distributed/optimized-gpt2-1b-vtestnet-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/distributed/optimized-gpt2-1b-vtestnet-v2

SGLang

How to use distributed/optimized-gpt2-1b-vtestnet-v2 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 "distributed/optimized-gpt2-1b-vtestnet-v2" \
    --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": "distributed/optimized-gpt2-1b-vtestnet-v2",
		"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 "distributed/optimized-gpt2-1b-vtestnet-v2" \
        --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": "distributed/optimized-gpt2-1b-vtestnet-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use distributed/optimized-gpt2-1b-vtestnet-v2 with Docker Model Runner:
```
docker model run hf.co/distributed/optimized-gpt2-1b-vtestnet-v2
```

kmfoda commited on Dec 3, 2024

Commit

bf2f8f6

verified ·

1 Parent(s): 593d4cb

Epoch 5. Batch Size 464. Peers 3.

Browse files

Files changed (3) hide show

config.json +1 -1
model.safetensors +1 -1
optimizer.pt +1 -1

config.json CHANGED Viewed

@@ -4,7 +4,7 @@
   "all_reduce_scores": {
     "0": "SUCCESS",
     "1": "SUCCESS",
-    "2": "SUCCESS",
     "3": "NON_PARTICIPATING",
     "4": "SUCCESS",
     "5": "NON_PARTICIPATING",

   "all_reduce_scores": {
     "0": "SUCCESS",
     "1": "SUCCESS",
+    "2": "NON_PARTICIPATING",
     "3": "NON_PARTICIPATING",
     "4": "SUCCESS",
     "5": "NON_PARTICIPATING",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1a62ec8ee7d99f3da5a155e98492ad42b3034837400aa3a5b6ab489846c3c6
 size 4040701744

 version https://git-lfs.github.com/spec/v1
+oid sha256:f48f3e2635ad1188156e0a0bb85b7da41901ee1ccfe74301d870d8c930ebd6ad
 size 4040701744

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc91baf07c21726afea827ca6355e42074e2d0f6ca264b6bc9d5934b567fabe5
 size 8081787874

 version https://git-lfs.github.com/spec/v1
+oid sha256:85fd60c568128be07a4dfd56ed98090005561330758ecd45c8c073d0c3b08388
 size 8081787874