Instructions to use Polygl0t/Tucano2-qwen-1.5B-Think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

nicholasKluge commited on Feb 5

Commit

5adb2b5

verified ·

1 Parent(s): c547a11

Upload training_config_apo.yaml with huggingface_hub

Browse files

Files changed (1) hide show

training_config_apo.yaml +98 -0

training_config_apo.yaml ADDED Viewed

	@@ -0,0 +1,98 @@

+# Directory settings
+checkpoint_dir: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think"
+train_dataset_dir:
+  # Total: 13,649 samples (x5 epochs)
+  # Harmfull samples (with reasoning): 4,008 samples
+  - /polyglot/portuguese/gigaverbo-v2-dpo/harmfull-reasoning
+  # Harmless samples (with reasoning): 9,641 samples
+  - /polyglot/portuguese/gigaverbo-v2-dpo/harmless-reasoning
+val_dataset_dir: null
+dataset_type: "jsonl"
+cache_dir: "/lustre/mlnvme/data/polyglot/.cache"
+# Data loading settings
+pin_memory: true
+num_workers_for_dataloader: 16
+shuffle_dataset: true
+mask_eos_token: false
+mask_pad_token: false
+# Model architecture settings
+vocab_size: 49152
+num_hidden_layers: 28
+num_attention_heads: 16
+num_key_value_heads: 8
+head_dim: 128
+hidden_size: 2048
+intermediate_size: 6144
+max_position_embeddings: 4096
+tie_word_embeddings: true
+hidden_act: "silu"
+output_hidden_states: false
+attn_implementation: "flash_attention_2"
+use_cache: false
+no_rope_layer_interval: null
+rope_theta: 1000000.0
+rope_scale_factor: null
+rms_norm_eps: 0.000001
+# Training settings
+total_batch_size: 524288
+micro_batch_size: 4
+gradient_accumulation_steps: 4
+eval_micro_batch_size: null
+num_train_epochs: 5
+warmup_ratio: 0.1
+max_learning_rate: 0.000005
+min_learning_rate: 0.0
+muon_learning_rate: null
+weight_decay: 0.0
+beta1: 0.9
+beta2: 0.95
+eps: 0.00000001
+lr_decay_type: "cosine"
+use_sqrt: false
+lr_decay_iters_coef: 1.
+seed: 42
+max_steps: 535
+max_grad_norm: 1.0
+# APO settings
+loss_type: "apo_zero"
+dpo_beta: 0.5
+precompute_ref_log_probs: true
+truncation_mode: "keep_end"
+# Precision and optimization settings
+torch_compile: false
+mat_mul_precision: "highest"
+tf32: true
+bf16: true
+gradient_checkpointing: true
+use_liger_kernel: false
+static_graph: false
+# Hub settings
+push_to_hub: false
+hub_token: null
+hub_model_id: null
+# Tokenizer and Reference model
+tokenizer_name_or_path: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think-SFT"
+chat_template_path: null
+reference_model: "/polyglot/portuguese/checkpoints/models/Tucano2-qwen-1.5B-Think-SFT"
+continual_pretraining: true
+# Checkpoint settings
+resume_from_checkpoint: null
+checkpointing_steps: 1000
+begin_new_stage: true
+stage_name: "single_cosine"
+# Miscellaneous settings
+sanity_check: false
+sanity_check_num_samples: 100000
+wandb_token: null
+wandb_id: "tucano2-qwen-1.5b-think-apo"
+wandb_project: "Polyglot"
+wandb_desc: "Developing LLMs for low-resource languages"