Instructions to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 with Transformers:

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

pipe = pipeline("text-generation", model="adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3")
model = AutoModelForMultimodalLM.from_pretrained("adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3

SGLang

How to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 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 "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3" \
    --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": "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3",
		"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 "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3" \
        --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": "adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3",
    max_seq_length=2048,
)

Docker Model Runner
How to use adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 with Docker Model Runner:
```
docker model run hf.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3
```

Another QLoRA DPO training of Yi-34B-200K. This time with sequence length 500, lora_r 16 and lora alpha 32. I was able to squeeze that in using Unsloth, script I used is in this repo. It definitely has much stronger effect than my previous one that was with lora_r 4, lora_alpha 8 and sequence length 200, but I am not sure if I didn't overcook it. Will try to train this on AEZAKMI v2 now.

Credits for mlabonne (I was using his Mistral fine-tuning script pieces for dataset preparation), Daniel Han and Michael Han (Unsloth AI team)

Downloads last month: 90

adamo1139
/

Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3

Dataset used to train adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3