Instructions to use BAAI/Infinity-Instruct-3M-0625-Llama3-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BAAI/Infinity-Instruct-3M-0625-Llama3-70B with Transformers:

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

pipe = pipeline("text-generation", model="BAAI/Infinity-Instruct-3M-0625-Llama3-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-3M-0625-Llama3-70B")
model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-3M-0625-Llama3-70B", 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 BAAI/Infinity-Instruct-3M-0625-Llama3-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BAAI/Infinity-Instruct-3M-0625-Llama3-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BAAI/Infinity-Instruct-3M-0625-Llama3-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BAAI/Infinity-Instruct-3M-0625-Llama3-70B

SGLang

How to use BAAI/Infinity-Instruct-3M-0625-Llama3-70B 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 "BAAI/Infinity-Instruct-3M-0625-Llama3-70B" \
    --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": "BAAI/Infinity-Instruct-3M-0625-Llama3-70B",
		"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 "BAAI/Infinity-Instruct-3M-0625-Llama3-70B" \
        --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": "BAAI/Infinity-Instruct-3M-0625-Llama3-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BAAI/Infinity-Instruct-3M-0625-Llama3-70B with Docker Model Runner:
```
docker model run hf.co/BAAI/Infinity-Instruct-3M-0625-Llama3-70B
```

hyxmmm commited on Jul 9, 2024

Commit

39a5bc0

verified ·

1 Parent(s): e64044c

Upload md5 with huggingface_hub

Browse files

Files changed (1) hide show

md5 +36 -0

md5 ADDED Viewed

	@@ -0,0 +1,36 @@

+26c9bc2b53c372a4207dac1fc6cc75fb  config.json
+efead4b67f76b346233b74441c632ad2  generation_config.json
+c7cb1e5634f9e88925a27e07d2cfd687  model-00001-of-00030.safetensors
+f64fa24cb6ed2dd933d35884782b66cf  model-00002-of-00030.safetensors
+d3518419098ee2f9ee2473c92cae7b05  model-00003-of-00030.safetensors
+b4ff6034f395696ba28920aa65f1cab1  model-00004-of-00030.safetensors
+b0564c67ac04392cae9d63a2e7118386  model-00005-of-00030.safetensors
+2d70116df47cb2f13afa62d4470b1b78  model-00006-of-00030.safetensors
+2ab0a6a4cb3c75998f0af25021fe85a2  model-00007-of-00030.safetensors
+7fa2600237bc95fa80985cd387b83af5  model-00008-of-00030.safetensors
+a6608a97bfdc8d384bdaca9e2deb2624  model-00009-of-00030.safetensors
+6b78860931a0cbd64561252616643ca6  model-00010-of-00030.safetensors
+2ddbebf4724213a64375a4af400f0d7b  model-00011-of-00030.safetensors
+3bbc9a4ddb0e04eeedb19bc87e05a7ee  model-00012-of-00030.safetensors
+41a4bf26c9aa216d23a5377f15ec1b46  model-00013-of-00030.safetensors
+43c6ade83c5768dea4ee4c6dd2b41816  model-00014-of-00030.safetensors
+8226e06487496a0afa976527842ca424  model-00015-of-00030.safetensors
+b2297851179161b4945fac56c9bc614a  model-00016-of-00030.safetensors
+2126ca3272b0f5fad634ecdce5219240  model-00017-of-00030.safetensors
+e02aa03bdafe74b2b5dc39eed32ff2c2  model-00018-of-00030.safetensors
+db34f57ee81166aa9f922626beb6d532  model-00019-of-00030.safetensors
+4cb63d1536b09057f97b894a0d91190f  model-00020-of-00030.safetensors
+7b542bf639d51b4b960a2e2bb3635f50  model-00021-of-00030.safetensors
+19362397ff1b128deae1621af5958dc4  model-00022-of-00030.safetensors
+4beaa95dd4407bc00aa268ef402b9f15  model-00023-of-00030.safetensors
+f1b96566d72a1a75002db06f1a6eaea8  model-00024-of-00030.safetensors
+4bb7dcbce811875b66608673ee1a0a11  model-00025-of-00030.safetensors
+6d126614d683e85a25262aaabf174c7b  model-00026-of-00030.safetensors
+4596efeedc9010207be98eefbdeae823  model-00027-of-00030.safetensors
+133935d3d2cd4641b4b0c52a1025c1e1  model-00028-of-00030.safetensors
+561f968996d676d21fa7014be09b2ca9  model-00029-of-00030.safetensors
+dca9edb51f691c332fafe422d556c919  model-00030-of-00030.safetensors
+619befe5bfadf56a2f8b435bc3b27fbe  model.safetensors.index.json
+33451ef46cbf550462128da373a66286  special_tokens_map.json
+ffcc9f7b5ef2191d144802baa72b1d3a  tokenizer.json
+8443e5855270a6ac6a4516e940f10817  tokenizer_config.json