Instructions to use TheREZOR/TinyTalk-UA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheREZOR/TinyTalk-UA with Transformers:

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

pipe = pipeline("text-generation", model="TheREZOR/TinyTalk-UA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheREZOR/TinyTalk-UA")
model = AutoModelForCausalLM.from_pretrained("TheREZOR/TinyTalk-UA", 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 TheREZOR/TinyTalk-UA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheREZOR/TinyTalk-UA

SGLang

How to use TheREZOR/TinyTalk-UA 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 "TheREZOR/TinyTalk-UA" \
    --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": "TheREZOR/TinyTalk-UA",
		"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 "TheREZOR/TinyTalk-UA" \
        --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": "TheREZOR/TinyTalk-UA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheREZOR/TinyTalk-UA with Docker Model Runner:
```
docker model run hf.co/TheREZOR/TinyTalk-UA
```

TinyTalk-UA / config.json

TheREZOR

TinyTalk UA — 9.96M Ukrainian chatbot for ESP32

9876813 verified 6 days ago

Raw

History Blame Contribute Delete

861 Bytes

	{
	"activation_function": "gelu_new",
	"architectures": [
	"GPTNeoForCausalLM"
	],
	"attention_dropout": 0.0,
	"attention_layers": [
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local"
	],
	"attention_types": [
	[
	[
	"global",
	"local"
	],
	4
	]
	],
	"bos_token_id": 0,
	"classifier_dropout": 0.1,
	"dtype": "float32",
	"embed_dropout": 0.0,
	"eos_token_id": 0,
	"hidden_size": 256,
	"initializer_range": 0.02,
	"intermediate_size": 1024,
	"layer_norm_epsilon": 1e-05,
	"max_position_embeddings": 256,
	"model_type": "gpt_neo",
	"num_heads": 16,
	"num_layers": 8,
	"pad_token_id": null,
	"resid_dropout": 0.0,
	"tie_word_embeddings": true,
	"transformers_version": "5.15.0",
	"use_cache": true,
	"vocab_size": 14000,
	"window_size": 256
	}