Instructions to use jakiAJK/internlm3-8b-instruct_AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jakiAJK/internlm3-8b-instruct_AWQ with Transformers:

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

pipe = pipeline("text-generation", model="jakiAJK/internlm3-8b-instruct_AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jakiAJK/internlm3-8b-instruct_AWQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jakiAJK/internlm3-8b-instruct_AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jakiAJK/internlm3-8b-instruct_AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jakiAJK/internlm3-8b-instruct_AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jakiAJK/internlm3-8b-instruct_AWQ

SGLang

How to use jakiAJK/internlm3-8b-instruct_AWQ 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 "jakiAJK/internlm3-8b-instruct_AWQ" \
    --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": "jakiAJK/internlm3-8b-instruct_AWQ",
		"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 "jakiAJK/internlm3-8b-instruct_AWQ" \
        --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": "jakiAJK/internlm3-8b-instruct_AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jakiAJK/internlm3-8b-instruct_AWQ with Docker Model Runner:
```
docker model run hf.co/jakiAJK/internlm3-8b-instruct_AWQ
```

Requirements

pip install -U transformers autoawq

Transformers inference

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16
device = "auto"

model_name = "jakiAJK/internlm3-8b-instruct_AWQ"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map= device, trust_remote_code= True, torch_dtype= dtype)

model.eval()

chat = [
    { "role": "user", "content": "List any 5 country capitals." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_tokens = tokenizer(chat, return_tensors="pt").to('cuda')

output = model.generate(**input_tokens, 
                        max_new_tokens=100)

output = tokenizer.batch_decode(output)

print(output)

Downloads last month: 4

Safetensors

Model size

9B params

Tensor type

I32

F16

Model tree for jakiAJK/internlm3-8b-instruct_AWQ

Base model

internlm/internlm3-8b-instruct

Quantized

(46)

this model