Instructions to use beyoru/ThinkAgain1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/ThinkAgain1.5 with Transformers:

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

pipe = pipeline("text-generation", model="beyoru/ThinkAgain1.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beyoru/ThinkAgain1.5")
model = AutoModelForCausalLM.from_pretrained("beyoru/ThinkAgain1.5", 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 beyoru/ThinkAgain1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/ThinkAgain1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/ThinkAgain1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/ThinkAgain1.5

SGLang

How to use beyoru/ThinkAgain1.5 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 "beyoru/ThinkAgain1.5" \
    --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": "beyoru/ThinkAgain1.5",
		"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 "beyoru/ThinkAgain1.5" \
        --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": "beyoru/ThinkAgain1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use beyoru/ThinkAgain1.5 with Docker Model Runner:
```
docker model run hf.co/beyoru/ThinkAgain1.5
```

ThinkAgain1.5 / README.md

beyoru

Update README.md

a8317df verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.17 kB

metadata

base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - text-generation-inference
  - transformers
  - qwen2
  - trl
  - sft
license: apache-2.0
language:
  - zho
  - eng
  - fra
  - spa
  - por
  - deu
  - ita
  - rus
  - jpn
  - kor
  - vie
  - tha
  - ara

Model detail

Reasoning natural and smarter
No system prompt training
LoRA training rank 16 and alpha 16
Tool calling support
Quanz this model may not get the best performance\

Usage:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.5"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()