Instructions to use Phind/Phind-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phind/Phind-70B with Transformers:

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

pipe = pipeline("text-generation", model="Phind/Phind-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Phind/Phind-70B")
model = AutoModelForCausalLM.from_pretrained("Phind/Phind-70B", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Phind/Phind-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phind/Phind-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phind/Phind-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Phind/Phind-70B

SGLang

How to use Phind/Phind-70B 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 "Phind/Phind-70B" \
    --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": "Phind/Phind-70B",
		"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 "Phind/Phind-70B" \
        --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": "Phind/Phind-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Phind/Phind-70B with Docker Model Runner:
```
docker model run hf.co/Phind/Phind-70B
```

michaelroyzen commited on Jan 30

Commit

9c08e97

verified ·

1 Parent(s): 4190053

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -20

README.md CHANGED Viewed

@@ -77,26 +77,6 @@ response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_token
 print(response)
 ```
-### With vLLM
-```python
-from vllm import LLM, SamplingParams
-llm = LLM(model="Phind/Phind-70B", tensor_parallel_size=4)
-sampling_params = SamplingParams(temperature=0.7, top_p=0.9, max_tokens=1024)
-prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-You are Phind, an intelligent assistant that helps with programming and technical questions.<|eot_id|><|start_header_id|>user<|end_header_id|}
-Write a Python function to find the longest palindromic substring.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-"""
-outputs = llm.generate([prompt], sampling_params)
-print(outputs[0].outputs[0].text)
-```
 ## Chat Template
 This model uses the Llama 3 chat format:

 print(response)
 ```
 ## Chat Template
 This model uses the Llama 3 chat format: