Instructions to use HuggingFaceH4/zephyr-7b-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/zephyr-7b-beta with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
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
Local Apps Settings

vLLM

How to use HuggingFaceH4/zephyr-7b-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/zephyr-7b-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/zephyr-7b-beta

SGLang

How to use HuggingFaceH4/zephyr-7b-beta 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 "HuggingFaceH4/zephyr-7b-beta" \
    --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": "HuggingFaceH4/zephyr-7b-beta",
		"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 "HuggingFaceH4/zephyr-7b-beta" \
        --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": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceH4/zephyr-7b-beta with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/zephyr-7b-beta
```

Update Open LLM Leaderboard source urls

#42

by Wauplin HF Staff - opened Dec 13, 2023

base: refs/heads/main

←

from: refs/pr/42

Discussion Files changed

-7

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ model-index:
          value: 0.6203071672354948
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # HellaSwag (10-shot)
   - task:
@@ -51,7 +51,7 @@ model-index:
          value: 0.8435570603465445
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # DROP (3-shot)
   - task:
@@ -69,7 +69,7 @@ model-index:
          value: 0.09662437080536909
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # TruthfulQA (0-shot)
   - task:
@@ -87,7 +87,7 @@ model-index:
          value: 0.5744916942762855
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # GSM8k (5-shot)
   - task:
@@ -106,7 +106,7 @@ model-index:
          value: 0.12736921910538287
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # MMLU (5-Shot)
   - task:
@@ -125,7 +125,7 @@ model-index:
          value: 0.6107
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # Winogrande (5-shot)
   - task:
@@ -144,7 +144,7 @@ model-index:
          value: 0.7774269928966061
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
   # AlpacaEval (taken from model card)
   - task:

          value: 0.6203071672354948
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # HellaSwag (10-shot)
   - task:
          value: 0.8435570603465445
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # DROP (3-shot)
   - task:
          value: 0.09662437080536909
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # TruthfulQA (0-shot)
   - task:
          value: 0.5744916942762855
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # GSM8k (5-shot)
   - task:
          value: 0.12736921910538287
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # MMLU (5-Shot)
   - task:
          value: 0.6107
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # Winogrande (5-shot)
   - task:
          value: 0.7774269928966061
     source:
       name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
   # AlpacaEval (taken from model card)
   - task: