Instructions to use blockblockblock/Code-Mistral-7B-bpw4.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Code-Mistral-7B-bpw4.6 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw4.6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/Code-Mistral-7B-bpw4.6")
model = AutoModelForCausalLM.from_pretrained("blockblockblock/Code-Mistral-7B-bpw4.6")
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 blockblockblock/Code-Mistral-7B-bpw4.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Code-Mistral-7B-bpw4.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Code-Mistral-7B-bpw4.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blockblockblock/Code-Mistral-7B-bpw4.6

SGLang

How to use blockblockblock/Code-Mistral-7B-bpw4.6 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 "blockblockblock/Code-Mistral-7B-bpw4.6" \
    --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": "blockblockblock/Code-Mistral-7B-bpw4.6",
		"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 "blockblockblock/Code-Mistral-7B-bpw4.6" \
        --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": "blockblockblock/Code-Mistral-7B-bpw4.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blockblockblock/Code-Mistral-7B-bpw4.6 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Code-Mistral-7B-bpw4.6
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Code-Mistral-7B

This Model is trained on refined version of my dataset Code-290k-ShareGPT. Besides this it is trained on following datasets:

Code-Feedback

orca-math-word-problems-200k

Openhermes

The idea was to check how this Model will perform with both Code & Maths datasets. This model is very good with Coding. Maths is still hit & miss but you can test out this model.

This Model is trained on massive datasets so the results are very good. I have used ChatML prompt format.

Kindly note this is qLoRA version, a rare exception.

Training: Entire dataset was trained on 4 x A100 80GB. For 3 epoch, training took almost 33 Hours. Axolotl codebase was used for training purpose. Entire data is trained on Mistral.

Example Prompt: This model uses ChatML prompt format.

<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

You can modify above Prompt as per your requirement.

I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.

Thank you for your love & support.

Example Output

C++

Error Resolving

Matrices

Machine Learning

Downloads last month: 7

blockblockblock
/

Code-Mistral-7B-bpw4.6

Datasets used to train blockblockblock/Code-Mistral-7B-bpw4.6