Instructions to use brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction with Transformers:

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

pipe = pipeline("text-generation", model="brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction")
model = AutoModelForMultimodalLM.from_pretrained("brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction")
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 brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction

SGLang

How to use brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction 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 "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction" \
    --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": "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction",
		"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 "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction" \
        --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": "brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction with Docker Model Runner:
```
docker model run hf.co/brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction
```

A bagel, with everything

Just a fiction oriented 6bpw exl2 quantization of https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2

Quantized on 300K tokens of two Vicuna format chats, a sci fi story and a fiction story at a long context. This should yield better storywriting performance than the default exl2 quantization.

Running

Being a Yi model, try running a lower temperature with ~0.05 MinP, a little repitition penalty, maybe mirostat with a low tau, and no other samplers. Yi tends to run "hot" by default.

24GB GPUs can run Yi-34B-200K models at 45K-75K context with exllamav2, and performant UIs like exui. I go into more detail in this post

Commands

First pass:

python convert.py --in_dir /home/alpha/FastModels/jondurbin_bagel-dpo-34b-v0.2 -o /home/alpha/FastModels/scratch -om /home/alpha/FastModels/bagelmeas.json --cal_dataset /home/alpha/Documents/stories.parquet -ml 32768 -mr 7 -ss 4096 -b 4.0 -hb 6 -nr

Second pass:

python convert.py --in_dir /home/alpha/FastModels/jondurbin_bagel-dpo-34b-v0.2 -o /home/alpha/FastModels/scratch -m /home/alpha/FastModels/bagelmeas.json --cal_dataset /home/alpha/Documents/stories.parquet -l 12288 -r 25 -ml 32768 -mr 9 -ss 4096 -b 4.0 -hb 6 -cf /home/alpha/FastModels/jondurbin_bagel-dpo-34b-v0.2-exl2-4bpw-fiction -nr

Downloads last month: 5

brucethemoose
/

jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction

A bagel, with everything

Running

Commands

Datasets used to train brucethemoose/jondurbin_bagel-dpo-34b-v0.2-exl2-6bpw-fiction