Instructions to use TheBloke/Mistral-7B-OpenOrca-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mistral-7B-OpenOrca-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Mistral-7B-OpenOrca-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-OpenOrca-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-OpenOrca-AWQ")
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 TheBloke/Mistral-7B-OpenOrca-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Mistral-7B-OpenOrca-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": "TheBloke/Mistral-7B-OpenOrca-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-OpenOrca-AWQ

SGLang

How to use TheBloke/Mistral-7B-OpenOrca-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 "TheBloke/Mistral-7B-OpenOrca-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": "TheBloke/Mistral-7B-OpenOrca-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 "TheBloke/Mistral-7B-OpenOrca-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": "TheBloke/Mistral-7B-OpenOrca-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/Mistral-7B-OpenOrca-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-OpenOrca-AWQ
```

RuntimeError: Unknown layout

by AkshatDogra - opened Feb 20, 2024

Discussion

AkshatDogra

Feb 20, 2024

Hi, I am gettting the error:

AutoAWQ/awq/modules/linear/gemm.py", line 46, in forward
    out = awq_ext.gemm_forward_cuda(
          ^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Unknown layout

when I am running the code:

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
import torch

model_name_or_path = "TheBloke/Mistral-7B-OpenOrca-AWQ"


# # Load model
model = AutoAWQForCausalLM.from_quantized(
    model_name_or_path,
    fuse_layers=True,
    device_map="auto",
    trust_remote_code=False,
    safetensors=True,
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    model_name_or_path,
    trust_remote_code=False,
    device_map="auto",
    low_cpu_mem_usage=True,
)

system_message = f"""[INST] <<SYS>>
You are a good and accurate assistant.
# """


prompt = "Who is answer to life,universe and everything?"
prompt_template = f"""<|im_start|>system
# {system_message}<|im_end|>
# <|im_start|>user
# {prompt}<|im_end|>
# <|im_start|>assistant
put's `attention_mask` to obtain reliable results.
# """

print("\n\n*** Generate:")

tokens = tokenizer(prompt_template, return_tensors="pt").input_ids.cuda()
# Generate output
generation_output = model.generate(
    tokens, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, max_new_tokens=512
)

print("Output: ", tokenizer.decode(generation_output[0]))

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment