Instructions to use mjmanashti/gemma-2b-ForexAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mjmanashti/gemma-2b-ForexAI with Transformers:

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

pipe = pipeline("text-generation", model="mjmanashti/gemma-2b-ForexAI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mjmanashti/gemma-2b-ForexAI")
model = AutoModelForCausalLM.from_pretrained("mjmanashti/gemma-2b-ForexAI")
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 mjmanashti/gemma-2b-ForexAI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mjmanashti/gemma-2b-ForexAI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mjmanashti/gemma-2b-ForexAI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mjmanashti/gemma-2b-ForexAI

SGLang

How to use mjmanashti/gemma-2b-ForexAI 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 "mjmanashti/gemma-2b-ForexAI" \
    --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": "mjmanashti/gemma-2b-ForexAI",
		"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 "mjmanashti/gemma-2b-ForexAI" \
        --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": "mjmanashti/gemma-2b-ForexAI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mjmanashti/gemma-2b-ForexAI with Docker Model Runner:
```
docker model run hf.co/mjmanashti/gemma-2b-ForexAI
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage

!pip install transformers

!pip install accelerate


from huggingface_hub import notebook_login
notebook_login()

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch


tokenizer = AutoTokenizer.from_pretrained("mjmanashti/gemma-2b-ForexAI")
torch.set_default_dtype(torch.float16)

model = AutoModelForCausalLM.from_pretrained("mjmanashti/gemma-2b-ForexAI", device_map="auto")

chat = [
    { "role": "user", "content": "Based on the following input data: [Time: 2024-01-29 23:00:00, Open: 1.0834, High: 1.0837, Low: 1.08334, Close: 1.08338, Volume: 722] what trading signal (BUY, SELL, or HOLD) should be executed to maximize profit? If the signal is BUY, what would be the entry price and If the signal is SELL, what would be the exit price for profit maximization? " },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
print(tokenizer.decode(outputs[0]))

Downloads last month: 28

Safetensors

Model size

3B params

Tensor type

F32

Model tree for mjmanashti/gemma-2b-ForexAI

Quantizations

2 models

mjmanashti
/

gemma-2b-ForexAI

Model Trained Using AutoTrain

Usage

Model tree for mjmanashti/gemma-2b-ForexAI

Spaces using mjmanashti/gemma-2b-ForexAI 2