Text Generation
Transformers
Safetensors
Portuguese
qwen3
text-generation-inference
conversational
Eval Results (legacy)
Instructions to use Polygl0t/Tucano2-qwen-1.5B-Think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Polygl0t/Tucano2-qwen-1.5B-Think with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Polygl0t/Tucano2-qwen-1.5B-Think") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Polygl0t/Tucano2-qwen-1.5B-Think") model = AutoModelForCausalLM.from_pretrained("Polygl0t/Tucano2-qwen-1.5B-Think", 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 Polygl0t/Tucano2-qwen-1.5B-Think with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Polygl0t/Tucano2-qwen-1.5B-Think" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Polygl0t/Tucano2-qwen-1.5B-Think", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Polygl0t/Tucano2-qwen-1.5B-Think
- SGLang
How to use Polygl0t/Tucano2-qwen-1.5B-Think 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 "Polygl0t/Tucano2-qwen-1.5B-Think" \ --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": "Polygl0t/Tucano2-qwen-1.5B-Think", "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 "Polygl0t/Tucano2-qwen-1.5B-Think" \ --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": "Polygl0t/Tucano2-qwen-1.5B-Think", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Polygl0t/Tucano2-qwen-1.5B-Think with Docker Model Runner:
docker model run hf.co/Polygl0t/Tucano2-qwen-1.5B-Think
Update README.md
Browse files
README.md
CHANGED
|
@@ -524,28 +524,28 @@ The table below compares the Tucano2 series against other base models of similar
|
|
| 524 |
|
| 525 |
</details>
|
| 526 |
|
| 527 |
-
| | Aggregate NPM | NPM Easy | NPM Hard | NPM Instruction | BLUEX
|
| 528 |
-
| -------------------------- | ------------- | -------- | -------- | --------------- | -----
|
| 529 |
-
| Qwen2.5-7B-Instruct | 58.
|
| 530 |
-
| Jurema-7B | 54.
|
| 531 |
-
|
|
| 532 |
-
|
|
| 533 |
-
|
|
| 534 |
-
| Qwen2.5-3B-Instruct | 47.
|
| 535 |
-
| Qwen2.5-1.5B-Instruct | 43.
|
| 536 |
-
| Tucano2-qwen-1.5B-Instruct | 42.
|
| 537 |
-
| Llama-3.2-3B-Instruct | 39.
|
| 538 |
-
| Tucano2-qwen-1.5B-Think | 30.
|
| 539 |
-
| Qwen3-1.7B | 29.
|
| 540 |
-
| Tucano2-qwen-0.5B-Instruct | 29.
|
| 541 |
-
| Qwen3-0.6B | 29.
|
| 542 |
-
| Qwen3-4B | 23.
|
| 543 |
-
| Qwen2.5-0.5B-Instruct | 21.
|
| 544 |
-
| Tucano2-qwen-0.5B-Think | 19.
|
| 545 |
-
| Llama-3.2-1B-Instruct | 17.
|
| 546 |
-
| Tucano-2b4-Instruct | 9.
|
| 547 |
-
| Tucano-1b1-Instruct | 7.
|
| 548 |
-
| TeenyTinyLlama-460m-Chat | 3.
|
| 549 |
|
| 550 |
<details>
|
| 551 |
<summary><b>Performance Comparison</b></summary>
|
|
|
|
| 524 |
|
| 525 |
</details>
|
| 526 |
|
| 527 |
+
| | Aggregate NPM | NPM Easy | NPM Hard | NPM Instruction | BLUEX | ENEM | OAB | ARC Challenge | BELEBELE | CALAME | Global PIQA | HellaSwag | LAMBADA | MMLU | IFEval-PT (prompt) | IFEval-PT (instruction) | GSM8K-PT (flex) |
|
| 528 |
+
| -------------------------- | ------------- | -------- | -------- | --------------- | ----- | ----- | ----- | ------------- | -------- | ------ | ----------- | --------- | ------- | ----- | ------------------ | ----------------------- | --------------- |
|
| 529 |
+
| Qwen2.5-7B-Instruct | 58.96 | 50.35 | 59.37 | 72.63 | 65.79 | 73.9 | 52.76 | 49.57 | 88 | 49.76 | 78 | 64.19 | 60.97 | 64.47 | 75.33 | 80.23 | 62.33 |
|
| 530 |
+
| Jurema-7B | 54.66 | 58.15 | 57.52 | 44.06 | 63.42 | 70.96 | 64.97 | 52.56 | 88.44 | 64.69 | 79 | 67.32 | 74.89 | 49.91 | 47 | 54.88 | 30.29 |
|
| 531 |
+
| Tucano2-qwen-3.7B-Think | 52.62 | 54.31 | 56.26 | 43.72 | 63 | 71.52 | 53.76 | 55.38 | 83.56 | 56.45 | 82 | 65.21 | 56.96 | 61.18 | 31.67 | 42.79 | 56.7 |
|
| 532 |
+
| Gemma-3-Gaia-PT-BR-4b-it | 51.67 | 49.67 | 44.82 | 66.43 | 50.9 | 64.52 | 43.46 | 54.7 | 78.89 | 51.88 | 77 | 62.21 | 53.25 | 51.49 | 70.33 | 77.67 | 51.29 |
|
| 533 |
+
| SmolLM3-3B | 50.92 | 51.16 | 43.37 | 63.11 | 48.68 | 60.88 | 42.23 | 52.82 | 78.44 | 60.4 | 71 | 63.16 | 65.4 | 53.3 | 69 | 74.88 | 45.43 |
|
| 534 |
+
| Qwen2.5-3B-Instruct | 47.91 | 36.09 | 51.44 | 61.75 | 56.88 | 68.65 | 46.79 | 41.71 | 84 | 45.76 | 67 | 58.44 | 33.82 | 58.22 | 63.33 | 70 | 51.9 |
|
| 535 |
+
| Qwen2.5-1.5B-Instruct | 43.21 | 41.49 | 43.98 | 44.8 | 52.02 | 61.79 | 44.28 | 39.74 | 76 | 56.74 | 69 | 50.21 | 59.44 | 51.91 | 42 | 50.23 | 42.16 |
|
| 536 |
+
| Tucano2-qwen-1.5B-Instruct | 42.61 | 45.89 | 44.78 | 33.52 | 52.85 | 62.7 | 43.42 | 50.26 | 77.56 | 54.38 | 71 | 55.25 | 59.05 | 52.54 | 34.33 | 46.51 | 19.71 |
|
| 537 |
+
| Llama-3.2-3B-Instruct | 39.85 | 21.77 | 44.24 | 62.67 | 52.02 | 59.13 | 44.97 | 43.93 | 78.56 | 0.39 | 71 | 55.83 | 0.12 | 52.14 | 62.67 | 70.23 | 55.1 |
|
| 538 |
+
| Tucano2-qwen-1.5B-Think | 30.09 | 29.9 | 28.01 | 33.87 | 39.22 | 39.89 | 34.26 | 42.82 | 67.67 | 11.13 | 74 | 54.95 | 26.7 | 43.3 | 33.67 | 45.12 | 22.83 |
|
| 539 |
+
| Qwen3-1.7B | 29.83 | 9.68 | 34.85 | 55.07 | 54.1 | 60.6 | 41.59 | 36.67 | 64.89 | 0.14 | 56 | 40.45 | 0.1 | 30.56 | 65 | 73.26 | 26.94 |
|
| 540 |
+
| Tucano2-qwen-0.5B-Instruct | 29.78 | 27.81 | 31.54 | 30.12 | 40.33 | 53.6 | 40.73 | 38.63 | 62.33 | 30.01 | 62 | 47.83 | 36.43 | 41.46 | 30 | 41.86 | 18.49 |
|
| 541 |
+
| Qwen3-0.6B | 29.67 | 19.05 | 27.96 | 50.2 | 40.61 | 45.91 | 36.04 | 32.39 | 60.89 | 39.31 | 49 | 37.2 | 31.83 | 41.12 | 55 | 63.95 | 31.66 |
|
| 542 |
+
| Qwen3-4B | 23.18 | 16.49 | 2.33 | 69.07 | 6.82 | 6.02 | 1.41 | 43.08 | 83.67 | 0.48 | 65 | 45.87 | 0.04 | 26.93 | 81 | 85.58 | 40.64 |
|
| 543 |
+
| Qwen2.5-0.5B-Instruct | 21.49 | 20.94 | 17.38 | 29.26 | 30.18 | 34.08 | 29.34 | 27.44 | 50.67 | 45.76 | 50 | 37.74 | 38.72 | 39.54 | 31 | 42.09 | 14.69 |
|
| 544 |
+
| Tucano2-qwen-0.5B-Think | 19.28 | 21.26 | 12.54 | 27.19 | 34.49 | 31.98 | 27.02 | 32.74 | 36.11 | 9.49 | 68 | 47.21 | 20.86 | 36.08 | 27.67 | 39.3 | 14.61 |
|
| 545 |
+
| Llama-3.2-1B-Instruct | 17.91 | 6.87 | 14.13 | 42.62 | 30.04 | 34.01 | 30.84 | 32.82 | 41.56 | 0.92 | 49 | 43.62 | 0.16 | 35.15 | 44.33 | 56.98 | 26.56 |
|
| 546 |
+
| Tucano-2b4-Instruct | 9.36 | 14.46 | 1.53 | 13.9 | 25.87 | 20.01 | 26.74 | 31.97 | 24 | 0.48 | 67 | 46.35 | 0.04 | 26.72 | 15 | 24.65 | 2.05 |
|
| 547 |
+
| Tucano-1b1-Instruct | 7.73 | 12.03 | 0.32 | 12.91 | 22.95 | 19.94 | 25.33 | 30 | 24.89 | 0 | 64 | 44.1 | 0 | 25.59 | 13.33 | 23.72 | 1.67 |
|
| 548 |
+
| TeenyTinyLlama-460m-Chat | 3.96 | 6.58 | -3.25 | 11.62 | 17.25 | 18.19 | 19.73 | 26.84 | 22.89 | 0 | 59 | 34.34 | 0 | 26.97 | 12.33 | 20.47 | 2.05 |
|
| 549 |
|
| 550 |
<details>
|
| 551 |
<summary><b>Performance Comparison</b></summary>
|