Instructions to use hllj/sft-zephyr-7b-beta-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hllj/sft-zephyr-7b-beta-v2 with Transformers:

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

pipe = pipeline("text-generation", model="hllj/sft-zephyr-7b-beta-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hllj/sft-zephyr-7b-beta-v2")
model = AutoModelForCausalLM.from_pretrained("hllj/sft-zephyr-7b-beta-v2", 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 hllj/sft-zephyr-7b-beta-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hllj/sft-zephyr-7b-beta-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hllj/sft-zephyr-7b-beta-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hllj/sft-zephyr-7b-beta-v2

SGLang

How to use hllj/sft-zephyr-7b-beta-v2 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 "hllj/sft-zephyr-7b-beta-v2" \
    --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": "hllj/sft-zephyr-7b-beta-v2",
		"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 "hllj/sft-zephyr-7b-beta-v2" \
        --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": "hllj/sft-zephyr-7b-beta-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hllj/sft-zephyr-7b-beta-v2 with Docker Model Runner:
```
docker model run hf.co/hllj/sft-zephyr-7b-beta-v2
```

sft-zephyr-7b-beta-v2

This model is a fine-tuned version of hllj/zephyr-7b-beta-vi-math on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4432

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-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3943	0.35	500	0.4903
0.3796	0.69	1000	0.4698
0.353	1.04	1500	0.4521
0.3173	1.39	2000	0.4463
0.3276	1.73	2500	0.4431

Framework versions

Transformers 4.35.2
Pytorch 2.1.0
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 5

Model tree for hllj/sft-zephyr-7b-beta-v2

Base model

hllj/zephyr-7b-beta-vi-math

Finetuned

(6)

this model