Instructions to use dfurman/Llama-3-8B-Orpo-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dfurman/Llama-3-8B-Orpo-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="dfurman/Llama-3-8B-Orpo-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dfurman/Llama-3-8B-Orpo-v0.1")
model = AutoModelForCausalLM.from_pretrained("dfurman/Llama-3-8B-Orpo-v0.1", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dfurman/Llama-3-8B-Orpo-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dfurman/Llama-3-8B-Orpo-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dfurman/Llama-3-8B-Orpo-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dfurman/Llama-3-8B-Orpo-v0.1

SGLang

How to use dfurman/Llama-3-8B-Orpo-v0.1 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 "dfurman/Llama-3-8B-Orpo-v0.1" \
    --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": "dfurman/Llama-3-8B-Orpo-v0.1",
		"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 "dfurman/Llama-3-8B-Orpo-v0.1" \
        --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": "dfurman/Llama-3-8B-Orpo-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dfurman/Llama-3-8B-Orpo-v0.1 with Docker Model Runner:
```
docker model run hf.co/dfurman/Llama-3-8B-Orpo-v0.1
```

dfurman commited on Apr 28, 2024

Commit

3f07b4b

verified ·

1 Parent(s): 79a5c2b

Upload LlamaForCausalLM

Browse files

Files changed (5) hide show

README.md +2 -2
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

README.md CHANGED Viewed

@@ -8,10 +8,10 @@ tags:
 - llama 3
 - rlhf
 - sft
-datasets:
-- mlabonne/orpo-dpo-mix-40k
 base_model:
 - meta-llama/Meta-Llama-3-8B
 ---
 # dfurman/Llama-3-8B-Orpo-v0.1

 - llama 3
 - rlhf
 - sft
 base_model:
 - meta-llama/Meta-Llama-3-8B
+datasets:
+- mlabonne/orpo-dpo-mix-40k
 ---
 # dfurman/Llama-3-8B-Orpo-v0.1

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c4b427722ac69d0fccb01ce7131271b70c2cbcebfadc0e4637bfd5fd4475e26
 size 4976714976

 version https://git-lfs.github.com/spec/v1
+oid sha256:907237ba31521dc9c2e754f65aae983e6d84a698d2f1c6318a74fd78fe856f73
 size 4976714976

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95da42c173ef74ff16373aba168eb7c5ac05cdf4e8850207bc5ca6ed8a588bbd
 size 4999802616

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d36c8d400a38c4a3c24cc6a19859354963685125bc5043ce67acdcd1a6fd838
 size 4999802616

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de73bfe82b0b2bb70a5555d7430f0fff43f182abe10f1dba9e978023d767bc91
 size 4915916080

 version https://git-lfs.github.com/spec/v1
+oid sha256:f34df12505f4997b4970360675452a72197ae0ad3ec223b5daed82cdaa110e25
 size 4915916080

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6325b463d95ca4c066fa448bb6d7d0cd0dd0146e44435a8975b62d8057e77860
 size 1168155192

 version https://git-lfs.github.com/spec/v1
+oid sha256:f34c205c15dcc9450bd8f1fac1c148d2ee8af017377676282b6991ae858035e2
 size 1168155192