Instructions to use Nondzu/Mistral-7B-code-16k-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nondzu/Mistral-7B-code-16k-qlora with Transformers:

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

pipe = pipeline("text-generation", model="Nondzu/Mistral-7B-code-16k-qlora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nondzu/Mistral-7B-code-16k-qlora")
model = AutoModelForCausalLM.from_pretrained("Nondzu/Mistral-7B-code-16k-qlora", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nondzu/Mistral-7B-code-16k-qlora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nondzu/Mistral-7B-code-16k-qlora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nondzu/Mistral-7B-code-16k-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nondzu/Mistral-7B-code-16k-qlora

SGLang

How to use Nondzu/Mistral-7B-code-16k-qlora 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 "Nondzu/Mistral-7B-code-16k-qlora" \
    --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": "Nondzu/Mistral-7B-code-16k-qlora",
		"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 "Nondzu/Mistral-7B-code-16k-qlora" \
        --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": "Nondzu/Mistral-7B-code-16k-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nondzu/Mistral-7B-code-16k-qlora with Docker Model Runner:
```
docker model run hf.co/Nondzu/Mistral-7B-code-16k-qlora
```

Nondzu commited on Oct 16, 2023

Commit

0eca161

1 Parent(s): 9ef9315

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -2

README.md CHANGED Viewed

@@ -1,8 +1,16 @@
 ---
 license: apache-2.0
 ---
-Prompt template: Alpaca
 ```
 Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -13,7 +21,7 @@ Below is an instruction that describes a task. Write a response that appropriate
 ```
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
-settings:
 ```
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 base_model_config: mistralai/Mistral-7B-Instruct-v0.1

 ---
 license: apache-2.0
 ---
+# Mistral-7B-code-16k-qlora
+I'm excited to announce the release of a new model called Mistral-7B-code-16k-qlora. This small and fast model shows a lot of promise for supporting coding or acting as a copilot. I'm currently looking for people to help me test it out!
+## Additional Information
+This model was trained on 3x RTX 3090 in my homelab, using around 130kWh for approximately 23 cents, which is equivalent to around $30 for electricity.
+## Prompt template: Alpaca
 ```
 Below is an instruction that describes a task. Write a response that appropriately completes the request.
 ```
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+## Settings:
 ```
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 base_model_config: mistralai/Mistral-7B-Instruct-v0.1