Instructions to use distributed/optimized-gpt2-2b-without-stable-embeddings with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distributed/optimized-gpt2-2b-without-stable-embeddings with Transformers:

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

pipe = pipeline("text-generation", model="distributed/optimized-gpt2-2b-without-stable-embeddings", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("distributed/optimized-gpt2-2b-without-stable-embeddings", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use distributed/optimized-gpt2-2b-without-stable-embeddings with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "distributed/optimized-gpt2-2b-without-stable-embeddings"
# 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-gpt2-2b-without-stable-embeddings",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/distributed/optimized-gpt2-2b-without-stable-embeddings

SGLang

How to use distributed/optimized-gpt2-2b-without-stable-embeddings 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-gpt2-2b-without-stable-embeddings" \
    --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-gpt2-2b-without-stable-embeddings",
		"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-gpt2-2b-without-stable-embeddings" \
        --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-gpt2-2b-without-stable-embeddings",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use distributed/optimized-gpt2-2b-without-stable-embeddings with Docker Model Runner:
```
docker model run hf.co/distributed/optimized-gpt2-2b-without-stable-embeddings
```

kmfoda commited on Dec 24, 2024

Commit

67b53f8

verified ·

1 Parent(s): 5a87058

Epoch 0. Batch Size 80. Peers 0.

Browse files

Files changed (4) hide show

config.json +3 -3
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1
optimizer.pt +3 -0

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/optimized-gpt2-2b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -264,8 +264,8 @@
   ],
   "attn_pdrop": 0.1,
   "auto_map": {
-    "AutoConfig": "configuration_gpt_optimized.GPTOptimConfig",
-    "AutoModelForCausalLM": "modeling_gpt_optimized.GPTOptim"
   },
   "block_size": 1024,
   "bos_token_id": 50256,

 {
+  "_name_or_path": "distributed/optimized-gpt2-2b-without-stable-embeddings",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
   ],
   "attn_pdrop": 0.1,
   "auto_map": {
+    "AutoConfig": "distributed/optimized-gpt2-2b-without-stable-embeddings--configuration_gpt_optimized.GPTOptimConfig",
+    "AutoModelForCausalLM": "distributed/optimized-gpt2-2b-without-stable-embeddings--modeling_gpt_optimized.GPTOptim"
   },
   "block_size": 1024,
   "bos_token_id": 50256,

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4225de00c48f00fd29861dc910ab84c8c146ca3b7860ef625a75249e1fb7ebfc
 size 4975530824

 version https://git-lfs.github.com/spec/v1
+oid sha256:3672b53c226d30983302cfa80c8150c581d305ff1d1203f969b1f0615ef3983e
 size 4975530824

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971cf897a6918dd28c001b2e7cfc068c13d18abe0f5d4aae49e4c3229020ffc0
 size 3075942944

 version https://git-lfs.github.com/spec/v1
+oid sha256:94c2ed63a740dc1dcd96e0de216e9360f21222b24bd802898b8e57547077dd65
 size 3075942944

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e232a713945ce12e55e463ee502d54fd8769edcbee991c9fb46b22f3a772f1fe
+size 4675070692