Instructions to use Guilherme34/Reasoning-2.6-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Guilherme34/Reasoning-2.6-fixed with Transformers:

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

pipe = pipeline("text-generation", model="Guilherme34/Reasoning-2.6-fixed")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Guilherme34/Reasoning-2.6-fixed")
model = AutoModelForCausalLM.from_pretrained("Guilherme34/Reasoning-2.6-fixed", 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 Guilherme34/Reasoning-2.6-fixed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Guilherme34/Reasoning-2.6-fixed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Guilherme34/Reasoning-2.6-fixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Guilherme34/Reasoning-2.6-fixed

SGLang

How to use Guilherme34/Reasoning-2.6-fixed 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 "Guilherme34/Reasoning-2.6-fixed" \
    --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": "Guilherme34/Reasoning-2.6-fixed",
		"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 "Guilherme34/Reasoning-2.6-fixed" \
        --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": "Guilherme34/Reasoning-2.6-fixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Guilherme34/Reasoning-2.6-fixed with Docker Model Runner:
```
docker model run hf.co/Guilherme34/Reasoning-2.6-fixed
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a Remake, refined and better version of the KingNish Reasoning model.


pip install -U bitsandbytes

pip install -U transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

MAX_REASONING_TOKENS = 1024
MAX_RESPONSE_TOKENS = 512

model = AutoModelForCausalLM.from_pretrained("Guilherme34/Reasoning-2.6", token="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")

tokenizer = AutoTokenizer.from_pretrained("Guilherme34/Reasoning-2.6")

prompt = "hey, how are you?"
messages = [
    {"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)

# print("REASONING: " + reasoning_output)

# Generate answer
messages.append({"role": "reasoning", "content": reasoning_output})
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)

print("ANSWER: " + response_output)

Downloads last month: 11

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Guilherme34/Reasoning-2.6-fixed

Quantizations

5 models