Instructions to use luisastellet/tucano-metaphor-melhor-hp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luisastellet/tucano-metaphor-melhor-hp with Transformers:

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

pipe = pipeline("text-generation", model="luisastellet/tucano-metaphor-melhor-hp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luisastellet/tucano-metaphor-melhor-hp")
model = AutoModelForCausalLM.from_pretrained("luisastellet/tucano-metaphor-melhor-hp", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luisastellet/tucano-metaphor-melhor-hp with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/luisastellet/tucano-metaphor-melhor-hp

SGLang

How to use luisastellet/tucano-metaphor-melhor-hp 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 "luisastellet/tucano-metaphor-melhor-hp" \
    --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": "luisastellet/tucano-metaphor-melhor-hp",
		"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 "luisastellet/tucano-metaphor-melhor-hp" \
        --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": "luisastellet/tucano-metaphor-melhor-hp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use luisastellet/tucano-metaphor-melhor-hp with Docker Model Runner:
```
docker model run hf.co/luisastellet/tucano-metaphor-melhor-hp
```

luisastellet commited on Aug 31

Commit

f1c4bb9

verified ·

1 Parent(s): 5a34b3a

tokenizer modelo_melhor_hp

Browse files

Files changed (3) hide show

chat_template.jinja +83 -0
tokenizer.json +0 -0
tokenizer_config.json +27 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,83 @@

+{#- Handle tool/function calling setup #}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {#- Include system message if present #}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {#- Add tool calling instructions in Portuguese #}
+    {{- "# Tools / Ferramentas\n\nVocê pode chamar uma ou mais funções para auxiliar na consulta do usuário.\n\nVocê recebe assinaturas de funções dentro de tags XML <tools></tools>:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nPara cada chamada de função, retorne um objeto json com o nome da função e os argumentos dentro das tags XML <tool_call></tool_call>:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {#- Standard system message without tools #}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Process each message in the conversation #}
+{%- for message in messages %}
+    {#- Normalize content to string #}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {#- Handle user messages and non-first system messages #}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {#- Handle assistant messages without reasoning #}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {% generation %}
+        {{- content }}
+        {#- Add tool calls if present #}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {#- Normalize tool call format #}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>' }}
+        {% endgeneration %}
+    {#- Handle tool response messages #}
+    {%- elif message.role == "tool" %}
+        {#- Group consecutive tool responses under one user message #}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{#- Add generation prompt if requested #}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "eos_token_id": 2,
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "<|pad|>",
+  "pad_token_id": 49109,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<|unk|>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}