Instructions to use bhenrym14/airoboros-3_1-yi-34b-200k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhenrym14/airoboros-3_1-yi-34b-200k with Transformers:

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

pipe = pipeline("text-generation", model="bhenrym14/airoboros-3_1-yi-34b-200k")

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

tokenizer = AutoTokenizer.from_pretrained("bhenrym14/airoboros-3_1-yi-34b-200k")
model = AutoModelForCausalLM.from_pretrained("bhenrym14/airoboros-3_1-yi-34b-200k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhenrym14/airoboros-3_1-yi-34b-200k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bhenrym14/airoboros-3_1-yi-34b-200k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/airoboros-3_1-yi-34b-200k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bhenrym14/airoboros-3_1-yi-34b-200k

SGLang

How to use bhenrym14/airoboros-3_1-yi-34b-200k 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 "bhenrym14/airoboros-3_1-yi-34b-200k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/airoboros-3_1-yi-34b-200k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "bhenrym14/airoboros-3_1-yi-34b-200k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/airoboros-3_1-yi-34b-200k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bhenrym14/airoboros-3_1-yi-34b-200k with Docker Model Runner:
```
docker model run hf.co/bhenrym14/airoboros-3_1-yi-34b-200k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Instruction tune of Yi-34b-200k with Airoboros-3.1 (fp16)

Overview

This is larryvrh/Yi-34B-200K-Llamafied, with instruction tuning performed with Jon Durbin's jondurbin/airoboros-3.1 dataset. That base model is 01-ai/Yi-34B-200k, but using llama2 model definitions and tokenizer to remove any remote code requirements.

This is a (merged) QLoRA fine-tune (rank 64).

The finetune was performed with 1x RTX 6000 Ada (~80 hours to this checkpoint). Prompts were truncated to 4096 tokens (for speed and VRAM headroom).

I have done very little testing with this model, so feedback on real world performance is appreciated!

How to Use

Use as you would any other Hugging Face fp16 llama-2 model.

Prompting:

Model was trained with llama-2 chat prompt format. See jondurbin/airoboros-l2-13b-3.1.1 model card for details.

Downloads last month: 55

Safetensors

Model size

34B params

Tensor type

F16

Model tree for bhenrym14/airoboros-3_1-yi-34b-200k

Quantizations

3 models

bhenrym14
/

airoboros-3_1-yi-34b-200k

Instruction tune of Yi-34b-200k with Airoboros-3.1 (fp16)

Overview

How to Use

Prompting:

Model tree for bhenrym14/airoboros-3_1-yi-34b-200k

Dataset used to train bhenrym14/airoboros-3_1-yi-34b-200k