Instructions to use graphcore-rahult/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use graphcore-rahult/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="graphcore-rahult/gpt2-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("graphcore-rahult/gpt2-wikitext2")
model = AutoModelWithLMHead.from_pretrained("graphcore-rahult/gpt2-wikitext2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use graphcore-rahult/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "graphcore-rahult/gpt2-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "graphcore-rahult/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/graphcore-rahult/gpt2-wikitext2

SGLang

How to use graphcore-rahult/gpt2-wikitext2 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 "graphcore-rahult/gpt2-wikitext2" \
    --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": "graphcore-rahult/gpt2-wikitext2",
		"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 "graphcore-rahult/gpt2-wikitext2" \
        --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": "graphcore-rahult/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use graphcore-rahult/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/graphcore-rahult/gpt2-wikitext2
```

graphcore-rahult commited on Dec 7, 2022

Commit

8403bc3

1 Parent(s): a724ae2

Training in progress, step 500

Browse files

Files changed (4) hide show

config.json +1 -1
ipu_config.json +3 -3
pytorch_model.bin +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "_name_or_path": "gpt2",
   "activation_function": "gelu",
   "architectures": [
-    "PipelinedGPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,

   "_name_or_path": "gpt2",
   "activation_function": "gelu",
   "architectures": [
+    "PoptorchPipelinedGPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,

ipu_config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 64,
   "inference_device_iterations": 5,
-  "inference_replication_factor": 4,
   "ipus_per_replica": 4,
   "layers_per_ipu": [
     0,
@@ -20,8 +20,8 @@
   "optimum_version": "1.5.1",
   "output_mode": "final",
   "recompute_checkpoint_every_layer": true,
-  "replicated_tensor_sharding": true,
-  "replication_factor": 4,
   "seed": 42,
   "sharded_execution_for_inference": false,
   "transformers_version": "4.20.1"

   "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 64,
   "inference_device_iterations": 5,
+  "inference_replication_factor": 1,
   "ipus_per_replica": 4,
   "layers_per_ipu": [
     0,
   "optimum_version": "1.5.1",
   "output_mode": "final",
   "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": false,
+  "replication_factor": 1,
   "seed": 42,
   "sharded_execution_for_inference": false,
   "transformers_version": "4.20.1"

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098b3647c1fc1f6dfec838602e3c14650fbd27a60644c1c26daf1a7c42ab08fb
 size 261514473

 version https://git-lfs.github.com/spec/v1
+oid sha256:e70c1ea321b105434650988294a0d038f373574156c0036a3a1b263fac473a51
 size 261514473

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dddd72216e055d0fad617b0f2383e163d10a21c8b1ff31203432e057541bd3f
 size 2735

 version https://git-lfs.github.com/spec/v1
+oid sha256:4869f5fe88dbf550509285ebaef436d3fe02346852a455707d5b9ba2730fc64d
 size 2735