Marco333/qwen2.5-0.5b-game-commands-stt

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}

@misc{marco333_game_commands_2026,
  author       = {Marco333},
  title        = {Game Command Recognition from Noisy Speech-to-Text using Qwen2.5-0.5B},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/Marco333/qwen2.5-0.5b-game-commands-stt},
}

#include "llama.h"
#include "common.h"
#include <string>
#include <iostream>

// System prompt - must match what the model was trained with
const char* SYSTEM_PROMPT = 
    "You are a game command interpreter. The user's input is noisy speech-to-text "
    "from a microphone in a gaming environment. Your job is to identify the intended "
    "game command from the noisy input.\n\n"
    "Valid commands: Attack, CastSpell, CloseDoor, Crouch, Defend, DropItem, Heal, "
    "Interact, Jump, OpenDoor, OpenInventory, OpenMap, PauseGame, PickUp, Reload, "
    "SaveGame, Sprint, Stop, SwitchWeapon, UseItem\n\n"
    "Respond with ONLY a JSON object: {\"command\": \"<CommandName>\"}\n"
    "If the input doesn't match any command, respond: {\"command\": \"Unknown\"}";

// Build the prompt using Qwen2.5 chat template
std::string build_prompt(const std::string& stt_text) {
    return "<|im_start|>system\n" + std::string(SYSTEM_PROMPT) + "<|im_end|>\n"
           "<|im_start|>user\n" + stt_text + "<|im_end|>\n"
           "<|im_start|>assistant\n";
}

// Parse command from model output like: {"command": "OpenDoor"}
std::string parse_command(const std::string& output) {
    auto pos = output.find("\"command\": \"");
    if (pos == std::string::npos) pos = output.find("\"command\":\"");
    if (pos == std::string::npos) return "Unknown";
    
    pos = output.find("\"", pos + 11);
    if (pos == std::string::npos) return "Unknown";
    pos++;
    
    auto end = output.find("\"", pos);
    if (end == std::string::npos) return "Unknown";
    
    return output.substr(pos, end - pos);
}

int main() {
    // Initialize llama.cpp
    llama_backend_init();
    
    // Load model
    llama_model_params model_params = llama_model_default_params();
    llama_model* model = llama_model_load_from_file("model_q4.gguf", model_params);
    
    // Create context
    llama_context_params ctx_params = llama_context_default_params();
    ctx_params.n_ctx = 512;      // Short context is fine for commands
    ctx_params.n_batch = 512;
    llama_context* ctx = llama_init_from_model(model, ctx_params);
    
    // Get the tokenizer/vocab from the model
    const llama_vocab* vocab = llama_model_get_vocab(model);
    
    // === GAME LOOP: process STT input ===
    std::string stt_input = "opun da dur";  // Noisy STT from player mic
    
    // Build prompt
    std::string prompt = build_prompt(stt_input);
    
    // Tokenize
    std::vector<llama_token> tokens(512);
    int n_tokens = llama_tokenize(vocab, prompt.c_str(), prompt.size(),
                                   tokens.data(), tokens.size(), true, true);
    tokens.resize(n_tokens);
    
    // Create batch and evaluate prompt
    llama_batch batch = llama_batch_init(512, 0, 1);
    for (int i = 0; i < n_tokens; i++) {
        llama_batch_add(batch, tokens[i], i, {0}, false);
    }
    batch.logits[batch.n_tokens - 1] = true;
    llama_decode(ctx, batch);
    
    // Generate response (max ~30 tokens for JSON output)
    std::string response;
    int n_cur = n_tokens;
    
    for (int i = 0; i < 30; i++) {
        llama_token new_token = llama_sampler_sample(/* your sampler */, ctx, -1);
        
        // Stop at EOS or end of JSON
        if (llama_vocab_is_eog(vocab, new_token)) break;
        
        // Convert token to text
        char buf[64];
        int len = llama_token_to_piece(vocab, new_token, buf, sizeof(buf), 0, true);
        response.append(buf, len);
        
        // Stop if we see closing brace (JSON complete)
        if (response.find("}") != std::string::npos) break;
        
        // Prepare next token
        llama_batch_clear(batch);
        llama_batch_add(batch, new_token, n_cur, {0}, true);
        llama_decode(ctx, batch);
        n_cur++;
    }
    
    // Parse the command
    std::string command = parse_command(response);
    std::cout << "STT: '" << stt_input << "' -> Command: " << command << std::endl;
    // Output: STT: 'opun da dur' -> Command: OpenDoor
    
    // Now trigger game action based on command string
    // e.g. if (command == "OpenDoor") game->openNearestDoor();
    
    // Cleanup
    llama_batch_free(batch);
    llama_free(ctx);
    llama_model_free(model);
    llama_backend_free();
    
    return 0;
}

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'Marco333/qwen2.5-0.5b-game-commands-stt'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)