Instructions to use G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b with Transformers:

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

pipe = pipeline("text-generation", model="G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b")
model = AutoModelForCausalLM.from_pretrained("G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b

SGLang

How to use G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b 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 "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b" \
    --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": "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b",
		"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 "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b" \
        --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": "G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b with Docker Model Runner:
```
docker model run hf.co/G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b
```

Llama 7b not llama 3.1 8B

#10

by legolasyiu - opened Sep 11, 2024

Discussion

legolasyiu

Sep 11, 2024

According to config file, huggyllama/llama-7b
You using llama-7b , not llama 3.1-8B. Could you tell me why you name it llama 3.1-8B? Thanks

rombodawg

Sep 15, 2024

@legolasyiu this is a joke llm its not real

G-reen

Owner Sep 15, 2024

Incorrect, you can download the LLM and use it I assure you it is real.

rombodawg

Sep 15, 2024

@G-reen

Independent Benchmark Results:

GPQA: 100% (0-shot Reflection)
MMLU: 100% (0-shot Reflection)
HumanEval: 100% (0-shot Reflection)
MATH: 100% (0-shot Reflection)
GSM8K: 100% (0-shot Reflection)
IFEval: 100% (0-shot Reflection)
TruthfulQA: 0% (0-shot Reflection)

{
  "_name_or_path": "huggyllama/llama-7b",
  "architectures": [
    "LlamaForCausalLM"
  ],

"G-reen/gpt5o-reflexion-q-agi-llama-3.1-8b" (8b)

Model size 6.74B params

G-reen (Owner):
Incorrect, you can download the LLM and use it I assure you it is real.

G-reen

Owner Sep 15, 2024

The ignorant will tell you to deny the reality right in front of you!!!

rombodawg

Sep 16, 2024

@G-reen

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment