Instructions to use thomnis/Enlighten_Instruct_merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thomnis/Enlighten_Instruct_merged with Transformers:

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

pipe = pipeline("text-generation", model="thomnis/Enlighten_Instruct_merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thomnis/Enlighten_Instruct_merged")
model = AutoModelForCausalLM.from_pretrained("thomnis/Enlighten_Instruct_merged")
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 thomnis/Enlighten_Instruct_merged with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/thomnis/Enlighten_Instruct_merged

SGLang

How to use thomnis/Enlighten_Instruct_merged 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 "thomnis/Enlighten_Instruct_merged" \
    --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": "thomnis/Enlighten_Instruct_merged",
		"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 "thomnis/Enlighten_Instruct_merged" \
        --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": "thomnis/Enlighten_Instruct_merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thomnis/Enlighten_Instruct_merged with Docker Model Runner:
```
docker model run hf.co/thomnis/Enlighten_Instruct_merged
```

thomnis commited on Mar 31, 2024

Commit

8bd5fee

verified ·

1 Parent(s): f07e3bc

Upload MistralForCausalLM

Browse files

Files changed (3) hide show

model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3cd9373489fb0b1f16d1ca69942a75336c22ceb36d50805d5498d1e63755ab2
 size 4943162336

 version https://git-lfs.github.com/spec/v1
+oid sha256:22bf4940fbea193bf0fd8db19172bb3863d7449959c14198021575339b5fba1a
 size 4943162336

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1281e44545aa9019c54669b09ff72db7dd6a3909d8032d5ec6bf95a87e9d2b
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:10316c35bcad5ec3ee41db5ef5bfadf41b4eb6341bdb089b5ccbcf03c33748d0
 size 4999819336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56be5fc0116e668cfc14971252ec55ab6296b7c2b8c3d554158c2166eb13c6de
 size 4540516344

 version https://git-lfs.github.com/spec/v1
+oid sha256:8a59f0028ba140f1a6588920561c648ac0f2744c1ae3f27960f66eb8aca4f03a
 size 4540516344