GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
TK17250
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
TK17250
Model Tree
unsloth/Llama-3.2-11B-Vision-Instruct
Input Modalities
Output Modalities
Supported Functionality
The model is trained specifically on gameplay screenshots from three titles:
| Game | Genre |
|---|---|
| Fortnite | Battle Royale |
| Rocket League | Vehicular Soccer |
| VALORANT | Tactical FPS |
Commentary style and vocabulary (e.g. weapon names, map callouts, in-game terminology) are tailored to these three games. Performance on other games or genres outside this scope is not guaranteed, since the training data does not cover them.
Minimax-M3 as a teacher model, then quality-filtered using a 0–5 relevance/quality score before training.python
from transformers import AutoProcessor, AutoModelForVision2Seqfrom PIL import Imageimport torch processor = AutoProcessor.from_pretrained("TK17250/game-comment-vlm")model = AutoModelForVision2Seq.from_pretrained( "TK17250/game-comment-vlm", torch_dtype=torch.bfloat16, device_map="auto",) image = Image.open("your_gameplay_screenshot.jpg").convert("RGB") system_prompt = ( "You are a passionate live game commentator. You watch a screenshot from a " "video game and give a short, natural spoken-style comment on the gameplay " "moment, reacting to how good or bad the play looks.")user_prompt = "Comment on this gameplay moment." messages = [ {"role": "user", "content": [ {"type": "image"}, {"type": "text", "text": f"{system_prompt}\n\n{user_prompt}"} ]}] input_text = processor.apply_chat_template(messages, add_generation_prompt=True)inputs = processor(image, input_text, add_special_tokens=False, return_tensors="pt").to(model.device) output = model.generate(**inputs, max_new_tokens=128, temperature=0.7, min_p=0.1)print(processor.decode(output[0], skip_special_tokens=True))Note: This model's chat template does not support a separate
systemrole alongside image inputs. Combine the persona/system instruction directly into theusermessage text, as shown above.
python
from unsloth import FastVisionModelfrom transformers import TextStreamer model, tokenizer = FastVisionModel.from_pretrained("TK17250/game-comment-vlm", load_in_4bit=False)FastVisionModel.for_inference(model) # ... build messages/inputs as above using `tokenizer` instead of `processor`_ = model.generate(**inputs, streamer=TextStreamer(tokenizer, skip_prompt=True), max_new_tokens=128)from transformers import AutoProcessor, AutoModelForVision2Seqfrom PIL import Imageimport torch processor = AutoProcessor.from_pretrained("TK17250/game-comment-vlm")model = AutoModelForVision2Seq.from_pretrained( "TK17250/game-comment-vlm", torch_dtype=torch.bfloat16, device_map="auto",) image = Image.open("your_gameplay_screenshot.jpg").convert("RGB") system_prompt = ( "You are a passionate live game commentator. You watch a screenshot from a " "video game and give a short, natural spoken-style comment on the gameplay " "moment, reacting to how good or bad the play looks.")user_prompt = "Comment on this gameplay moment." messages = [ {"role": "user", "content": [ {"type": "image"}, {"type": "text", "text": f"{system_prompt}\n\n{user_prompt}"} ]}] input_text = processor.apply_chat_template(messages, add_generation_prompt=True)inputs = processor(image, input_text, add_special_tokens=False, return_tensors="pt").to(model.device) output = model.generate(**inputs, max_new_tokens=128, temperature=0.7, min_p=0.1)print(processor.decode(output[0], skip_special_tokens=True))from unsloth import FastVisionModelfrom transformers import TextStreamer model, tokenizer = FastVisionModel.from_pretrained("TK17250/game-comment-vlm", load_in_4bit=False)FastVisionModel.for_inference(model) # ... build messages/inputs as above using `tokenizer` instead of `processor`_ = model.generate(**inputs, streamer=TextStreamer(tokenizer, skip_prompt=True), max_new_tokens=128)