Instructions to use BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B with Transformers:

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

pipe = pipeline("text-generation", model="BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B")
model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B"
# 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-7M-Gen-Llama3_1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B

SGLang

How to use BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B 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-7M-Gen-Llama3_1-70B" \
    --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-7M-Gen-Llama3_1-70B",
		"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-7M-Gen-Llama3_1-70B" \
        --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-7M-Gen-Llama3_1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B with Docker Model Runner:
```
docker model run hf.co/BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B
```

nielsr HF Staff commited on Jun 16, 2025

Commit

ecc8a8f

verified ·

1 Parent(s): 1ef63c4

Add pipeline tag, library name and link to Github repo

Browse files

This PR adds the `pipeline_tag` and `library_name` to the model card, ensuring the model appears correctly in search results.
It also adds the link to the Github repo.

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -1,10 +1,13 @@
 ---
-license: llama3.1
 datasets:
 - BAAI/Infinity-Instruct
 language:
 - en
 ---
 # Infinity Instruct
 <p align="center">
@@ -39,7 +42,7 @@ Infinity-Instruct-7M-Gen-Llama3.1-70B is an opensource supervised instruction tu
 <img src="fig/trainingflow.png">
 </p>
-Infinity-Instruct-7M-Gen-Llama3.1-70B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Llama3.1-70B, and get the foundational instruct model Infinity-Instruct-7M-Llama3-70B. Then we finetune the Infinity-Instruct-7M-Llama3-70B to get the stronger chat model Infinity-Instruct-7M-Gen-Llama3_1-70B. Here is the training hyperparamers.
 ```bash
 epoch: 3
@@ -54,7 +57,7 @@ global_batch_size: 528
 clip_grad: 1.0
 ```
-Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatenate multiple training samples to remove padding token and apply diverse acceleration techniques to the traning procudure. It effectively reduces our training costs. We will release our code in the near future!
 ## **Benchmark**
@@ -76,7 +79,7 @@ Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatena
 ## **How to use**
-Infinity-Instruct-7M-Gen-Llama3_1-70B adopt the same chat template of [Llama3-70B-instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct):
 ```bash
 <|begin_of_text|><|start_header_id|>user<|end_header_id|>

 ---
 datasets:
 - BAAI/Infinity-Instruct
 language:
 - en
+license: llama3.1
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # Infinity Instruct
 <p align="center">
 <img src="fig/trainingflow.png">
 </p>
+Infinity-Instruct-7M-Gen-Llama3_1-70B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Llama3.1-70B, and get the foundational instruct model Infinity-Instruct-7M-Llama3-70B. Then we finetune the Infinity-Instruct-7M-Llama3-70B to get the stronger chat model Infinity-Instruct-7M-Gen-Llama3_1-70B. Here is the training hyperparamers.
 ```bash
 epoch: 3
 clip_grad: 1.0
 ```
+Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatenate multiple training samples to remove padding token and apply diverse acceleration techniques to the traning procudure. It effectively reduces our training costs. We will release our code in the near future! The code is available at: https://github.com/FlagOpen/FlagScale
 ## **Benchmark**
 ## **How to use**
+Infinity-Instruct-7M-Gen-Llama3_1-70B adopt the same chat template of [Llama3-70B-instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct):\
 ```bash
 <|begin_of_text|><|start_header_id|>user<|end_header_id|>