Instructions to use dicta-il/dictalm2.0-instruct-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dicta-il/dictalm2.0-instruct-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="dicta-il/dictalm2.0-instruct-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dicta-il/dictalm2.0-instruct-AWQ")
model = AutoModelForCausalLM.from_pretrained("dicta-il/dictalm2.0-instruct-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

vLLM

How to use dicta-il/dictalm2.0-instruct-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dicta-il/dictalm2.0-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": "dicta-il/dictalm2.0-instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dicta-il/dictalm2.0-instruct-AWQ

SGLang

How to use dicta-il/dictalm2.0-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 "dicta-il/dictalm2.0-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": "dicta-il/dictalm2.0-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 "dicta-il/dictalm2.0-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": "dicta-il/dictalm2.0-instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dicta-il/dictalm2.0-instruct-AWQ with Docker Model Runner:
```
docker model run hf.co/dicta-il/dictalm2.0-instruct-AWQ
```

dictalm2.0-instruct-AWQ model doesn't run without GPU

by noamikooo - opened May 7, 2025

Discussion

noamikooo

May 7, 2025

•

edited May 7, 2025

[Using Ubuntu]
The quantized dicta-il/dictalm2.0-instruct-AWQ model doesn't run on CPU without GPU.
I get the following error:

File "/home/dev/.local/share/virtualenvs/new_final-QzMsWVq1/lib/python3.11/site-packages/awq/modules/linear/gemm_ipex.py", line 18, in __init__
    assert IPEX_INSTALLED, \
           ^^^^^^^^^^^^^^
AssertionError: Please install IPEX package with `pip install intel_extension_for_pytorch`.

Installing the intel_extension_for_pytorch doesn't make a difference and the error persists.
Let alone the fact that I'm using an AMD CPU.

Also tried using various autoawq versions including 0.27 and 0.28

Any chance you guys can fix it?

P.S. -- The full Dicta 7B dicta-il/dictalm2.0-instruct runs well on machines with CPU only (no GPU).

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