Instructions to use ZharfaTech/ZharfaOpen-0309 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZharfaTech/ZharfaOpen-0309 with Transformers:

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

pipe = pipeline("text-generation", model="ZharfaTech/ZharfaOpen-0309")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZharfaTech/ZharfaOpen-0309")
model = AutoModelForCausalLM.from_pretrained("ZharfaTech/ZharfaOpen-0309", 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 ZharfaTech/ZharfaOpen-0309 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZharfaTech/ZharfaOpen-0309"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZharfaTech/ZharfaOpen-0309",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZharfaTech/ZharfaOpen-0309

SGLang

How to use ZharfaTech/ZharfaOpen-0309 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 "ZharfaTech/ZharfaOpen-0309" \
    --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": "ZharfaTech/ZharfaOpen-0309",
		"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 "ZharfaTech/ZharfaOpen-0309" \
        --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": "ZharfaTech/ZharfaOpen-0309",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZharfaTech/ZharfaOpen-0309 with Docker Model Runner:
```
docker model run hf.co/ZharfaTech/ZharfaOpen-0309
```

ZharfaOpen-0309 / eval.py

Habib

[INIT] First Checkpoint (2024-03-09)

13561bb over 2 years ago

Raw

History Blame Contribute Delete

1.45 kB

	import torch
	from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

	from peft import LoraConfig, PeftModel, prepare_model_for_kbit_training, get_peft_model

	model_id = "/share/models/open-zharfa"

	tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True)

	base_model = AutoModelForCausalLM.from_pretrained(
	model_id,
	low_cpu_mem_usage=True,
	return_dict=True,
	torch_dtype=torch.float16,
	device_map="auto",
	)

	base_model.generation_config.do_sample = True


	#tokenizer.pad_token = tokenizer.eos_token
	tokenizer.pad_token = tokenizer.unk_token
	tokenizer.padding_side = "right"

	def get_completion_merged(query: str, model, tokenizer) -> str:
	device = "cuda:0"

	prompt_template = """

	GPT4 Correct User: {query}<\|end_of_turn\|>GPT4 Correct Assistant:

	"""
	prompt = prompt_template.format(query=query)

	encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)

	model_inputs = encodeds.to(device)

	generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True, temperature=0.5, pad_token_id=tokenizer.unk_token_id) #pad_token_id=tokenizer.eos_token_id)
	decoded = tokenizer.batch_decode(generated_ids)
	return (decoded[0])

	while True:
	q = input('q : ')
	result = get_completion_merged(query=q, model=base_model, tokenizer=tokenizer)
	print(result)