Instructions to use PygTesting/pyg3v1-nemo-3ep-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PygTesting/pyg3v1-nemo-3ep-ckpts with Transformers:

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

pipe = pipeline("text-generation", model="PygTesting/pyg3v1-nemo-3ep-ckpts")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PygTesting/pyg3v1-nemo-3ep-ckpts")
model = AutoModelForCausalLM.from_pretrained("PygTesting/pyg3v1-nemo-3ep-ckpts")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PygTesting/pyg3v1-nemo-3ep-ckpts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PygTesting/pyg3v1-nemo-3ep-ckpts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PygTesting/pyg3v1-nemo-3ep-ckpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PygTesting/pyg3v1-nemo-3ep-ckpts

SGLang

How to use PygTesting/pyg3v1-nemo-3ep-ckpts 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 "PygTesting/pyg3v1-nemo-3ep-ckpts" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PygTesting/pyg3v1-nemo-3ep-ckpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "PygTesting/pyg3v1-nemo-3ep-ckpts" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PygTesting/pyg3v1-nemo-3ep-ckpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PygTesting/pyg3v1-nemo-3ep-ckpts with Docker Model Runner:
```
docker model run hf.co/PygTesting/pyg3v1-nemo-3ep-ckpts
```

TearGosling commited on Oct 14, 2024

Commit

af2226e

verified ·

1 Parent(s): 6a0cada

Training in progress, step 109

Browse files

Files changed (10) hide show

generation_config.json +7 -0
model-00001-of-00005.safetensors +1 -1
model-00002-of-00005.safetensors +1 -1
model-00003-of-00005.safetensors +1 -1
model-00004-of-00005.safetensors +1 -1
model-00005-of-00005.safetensors +1 -1
pytorch_model.bin +3 -0
special_tokens_map.json +1 -1
tokenizer_config.json +1 -1
training_args.bin +1 -1

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865159616627c93de47fcaf4a6c2c6f2630b9f3c41f99ac475461c9f188f2e6a
 size 4865522496

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d59e704b9332ca6671da25501a666dce516569fde678d02de4b13e4ad04de4
 size 4907529424

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4201fa373128c2ecdf897fd0a42fff9dd4f7a2b1df14824ed81c00c4594f99
 size 4907529456

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f7df4614f67c290f7294f59263abed169ad4c38c32ef76af7ba6c3ca9e5abf
 size 4907529456

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3b34a9d82f6e95cbb8a5ff80dba8a7d4d551e4024d25579618d56e455be8555
 size 4907496272

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b449aeb03898bfe17c0c7d6dcab2c5cf04efe827898a2e8dc6dd15e6df44834
+size 49706

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

@@ -8009,7 +8009,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }

 version https://git-lfs.github.com/spec/v1
+oid sha256:e345db40de4faa000f0d0213318a3422924a170129328eb87adc58eb76b6b486
 size 7544

	@@ -0,0 +1,7 @@

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