Instructions to use dbands/tantrum_16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbands/tantrum_16bit with Transformers:

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

pipe = pipeline("text-generation", model="dbands/tantrum_16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbands/tantrum_16bit")
model = AutoModelForCausalLM.from_pretrained("dbands/tantrum_16bit", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dbands/tantrum_16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbands/tantrum_16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbands/tantrum_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dbands/tantrum_16bit

SGLang

How to use dbands/tantrum_16bit 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 "dbands/tantrum_16bit" \
    --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": "dbands/tantrum_16bit",
		"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 "dbands/tantrum_16bit" \
        --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": "dbands/tantrum_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use dbands/tantrum_16bit with Docker Model Runner:
```
docker model run hf.co/dbands/tantrum_16bit
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

I created this model with the primary intent to review python code. This is a continued work in progress and I will update as time moves on.

Provide the model with python code and it will provide an analysis, which will include suggestions to improve the code.

This model can be used to generate prompts to in turn generate "clean" synthetic code bases for fine tuning models that generate python code for tool use.

base_model: cognitivecomputations/dolphin-2.9.2-qwen2-7b language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - qwen2 - trl

Uploaded model

Developed by: dbands
License: apache-2.0
Finetuned from model : cognitivecomputations/dolphin-2.9.2-qwen2-7b

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for dbands/tantrum_16bit

Base model

Qwen/Qwen2-7B

Finetuned

dphn/dolphin-2.9.2-qwen2-7b

Finetuned

(1)

this model

Quantizations

2 models

dbands
/

tantrum_16bit

base_model: cognitivecomputations/dolphin-2.9.2-qwen2-7b language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - qwen2 - trl

Uploaded model

Model tree for dbands/tantrum_16bit

Dataset used to train dbands/tantrum_16bit