Instructions to use tanliboy/lambda-qwen2.5-32b-dpo-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanliboy/lambda-qwen2.5-32b-dpo-test with Transformers:

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

pipe = pipeline("text-generation", model="tanliboy/lambda-qwen2.5-32b-dpo-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tanliboy/lambda-qwen2.5-32b-dpo-test")
model = AutoModelForCausalLM.from_pretrained("tanliboy/lambda-qwen2.5-32b-dpo-test")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tanliboy/lambda-qwen2.5-32b-dpo-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanliboy/lambda-qwen2.5-32b-dpo-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tanliboy/lambda-qwen2.5-32b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanliboy/lambda-qwen2.5-32b-dpo-test

SGLang

How to use tanliboy/lambda-qwen2.5-32b-dpo-test 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 "tanliboy/lambda-qwen2.5-32b-dpo-test" \
    --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": "tanliboy/lambda-qwen2.5-32b-dpo-test",
		"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 "tanliboy/lambda-qwen2.5-32b-dpo-test" \
        --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": "tanliboy/lambda-qwen2.5-32b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tanliboy/lambda-qwen2.5-32b-dpo-test with Docker Model Runner:
```
docker model run hf.co/tanliboy/lambda-qwen2.5-32b-dpo-test
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

lambda-qwen2.5-32b-dpo-test

This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the tanliboy/orca_dpo_pairs dataset. It achieves the following results on the evaluation set:

Loss: 0.0003
Rewards/chosen: -10.1618
Rewards/rejected: -26.1150
Rewards/accuracies: 1.0
Rewards/margins: 15.9532
Logps/rejected: -3049.5271
Logps/chosen: -1372.8903
Logits/rejected: -0.3154
Logits/chosen: -0.0600

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0103	0.2618	100	0.0060	-8.5159	-18.7731	1.0	10.2572	-2315.3333	-1208.2968	-0.5485	-0.2481
0.0005	0.5236	200	0.0005	-9.9255	-24.9117	1.0	14.9862	-2929.1948	-1349.2588	-0.3723	-0.0661
0.0005	0.7853	300	0.0004	-10.0873	-25.9319	1.0	15.8446	-3031.2175	-1365.4342	-0.2882	-0.0014

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 31

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for tanliboy/lambda-qwen2.5-32b-dpo-test

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Finetuned

(1217)

this model

Merges

10 models

Quantizations

3 models

tanliboy
/

lambda-qwen2.5-32b-dpo-test

lambda-qwen2.5-32b-dpo-test

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for tanliboy/lambda-qwen2.5-32b-dpo-test

Dataset used to train tanliboy/lambda-qwen2.5-32b-dpo-test

Space using tanliboy/lambda-qwen2.5-32b-dpo-test 1