Instructions to use weijie210/zephyr-7b-UC-0-B0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use weijie210/zephyr-7b-UC-0-B0.5 with Transformers:

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

pipe = pipeline("text-generation", model="weijie210/zephyr-7b-UC-0-B0.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("weijie210/zephyr-7b-UC-0-B0.5")
model = AutoModelForCausalLM.from_pretrained("weijie210/zephyr-7b-UC-0-B0.5", 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 weijie210/zephyr-7b-UC-0-B0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "weijie210/zephyr-7b-UC-0-B0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weijie210/zephyr-7b-UC-0-B0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/weijie210/zephyr-7b-UC-0-B0.5

SGLang

How to use weijie210/zephyr-7b-UC-0-B0.5 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 "weijie210/zephyr-7b-UC-0-B0.5" \
    --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": "weijie210/zephyr-7b-UC-0-B0.5",
		"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 "weijie210/zephyr-7b-UC-0-B0.5" \
        --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": "weijie210/zephyr-7b-UC-0-B0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use weijie210/zephyr-7b-UC-0-B0.5 with Docker Model Runner:
```
docker model run hf.co/weijie210/zephyr-7b-UC-0-B0.5
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

zephyr-7b-UC-0-B0.5

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1130
Rewards/chosen: -3.7732
Rewards/rejected: -13.4408
Rewards/accuracies: 0.8644
Rewards/margins: 9.6676
Logps/rejected: -173.6967
Logps/chosen: -189.7024
Logits/rejected: -2.8645
Logits/chosen: -2.9068

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: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
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
0.1262	0.62	500	0.1185	-3.0114	-12.1820	0.8670	9.1707	-171.1792	-188.1787	-2.8565	-2.9004

Framework versions

Transformers 4.36.1
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.15.0

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for weijie210/zephyr-7b-UC-0-B0.5

Base model

mistralai/Mistral-7B-v0.1

Finetuned

alignment-handbook/zephyr-7b-sft-full

Finetuned

(393)

this model

Quantizations

1 model