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

Libraries

How to use Nondzu/Mistral-7B-codealpaca-lora with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nondzu/Mistral-7B-codealpaca-lora")
model = AutoModelForCausalLM.from_pretrained("Nondzu/Mistral-7B-codealpaca-lora")
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

vLLM

How to use Nondzu/Mistral-7B-codealpaca-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nondzu/Mistral-7B-codealpaca-lora

SGLang

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

Docker Model Runner
How to use Nondzu/Mistral-7B-codealpaca-lora with Docker Model Runner:
```
docker model run hf.co/Nondzu/Mistral-7B-codealpaca-lora
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mistral-7B-codealpaca

I am thrilled to introduce my Mistral-7B-codealpaca model. This variant is optimized and demonstrates potential in assisting developers as a coding companion. I welcome contributions from testers and enthusiasts to help evaluate its performance.

Training Details

I trained the model using 3xRTX 3090 for 118 hours.

Quantised Model Links:

Download by qBittorrent:

Torrent file: https://github.com/Nondzu/LlamaTor/blob/torrents/torrents/Nondzu_Mistral-7B-codealpaca-lora.torrent

Dataset:

Dataset Name: theblackcat102/evol-codealpaca-v1
Dataset Link: theblackcat102/evol-codealpaca-v1

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Performance (evalplus)

Human eval plus: https://github.com/evalplus/evalplus

Well, the results are better than I expected:

Base: {'pass@1': 0.47560975609756095}
Base + Extra: {'pass@1': 0.4329268292682927}

For reference, I've provided the performance of the original Mistral model alongside my Mistral-7B-code-16k-qlora model.

** Nondzu/Mistral-7B-code-16k-qlora**:

Base: {'pass@1': 0.3353658536585366}
Base + Extra: {'pass@1': 0.2804878048780488}

** mistralai/Mistral-7B-Instruct-v0.1**:

Base: {'pass@1': 0.2926829268292683}
Base + Extra: {'pass@1': 0.24390243902439024}

Model Configuration:

Here are the configurations for my Mistral-7B-codealpaca-lora:

base_model: mistralai/Mistral-7B-Instruct-v0.1
base_model_config: mistralai/Mistral-7B-Instruct-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
  - path: theblackcat102/evol-codealpaca-v1
    type: oasst
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./nondzu/Mistral-7B-codealpaca-test14
adapter: lora
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true

Additional Projects:

For other related projects, you can check out:

LlamaTor on GitHub

Downloads last month: 227

Safetensors

Model size

7B params

Tensor type

F16

Model tree for Nondzu/Mistral-7B-codealpaca-lora

Merges

224 models

Quantizations

5 models

Nondzu
/

Mistral-7B-codealpaca-lora