GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Cochon123
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Cochon123
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
Given a board (15×15 char grid; . = empty, lowercase = placed blank) and a
rack, output one play_move JSON object placing only newly-added tiles:
json
{"tool":"play_move","arguments":{"placements":[{"row":3,"col":10,"letter":"A"}]}}Cochon123/scrabble-cot-dataset
(rack + best move + score + play_move JSON), ~300 tokens/example.
Compact data: Cochon123/scrabble-compact-train.board grid + rack string (see
prompt_format.py). Important: use this exact prompt at inference — the
model was not trained on the verbose per-tile JSON prompt.Scored with the benchmark_scrabble
solver (ENABLE lexicon) and the leaderboard metric:
text
score_pct = 100 * sum(model_move_score) / sum(optimal_score)2nd place on the public leaderboard (DeepSeek V4 Pro) = 27.8 %.
python
from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModelimport torch, json BASE = "Qwen/Qwen3-4B"; ADAPTER = "Cochon123/qwen3-4b-scrabble"tok = AutoTokenizer.from_pretrained(ADAPTER)model = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="cuda")model = PeftModel.from_pretrained(model, ADAPTER).eval() board = ["."*15]*15 # 15 strings of 15 charsboard[7] = ".......CAT......." # place existing tilesrack = "AEGHOUV"msgs = [{"role":"system","content":"Pick the highest-scoring legal Scrabble move..."}, {"role":"user","content":json.dumps({"rack":rack,"board":board})}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True, enable_thinking=False)out = model.generate(**tok(text, return_tensors="pt").to("cuda"), max_new_tokens=120, do_sample=False)print(tok.decode(out[0][tok(text, return_tensors="pt")["input_ids"].shape[1]:], skip_special_tokens=True)){"tool":"play_move","arguments":{"placements":[{"row":3,"col":10,"letter":"A"}]}}from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModelimport torch, json BASE = "Qwen/Qwen3-4B"; ADAPTER = "Cochon123/qwen3-4b-scrabble"tok = AutoTokenizer.from_pretrained(ADAPTER)model = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="cuda")model = PeftModel.from_pretrained(model, ADAPTER).eval() board = ["."*15]*15 # 15 strings of 15 charsboard[7] = ".......CAT......." # place existing tilesrack = "AEGHOUV"msgs = [{"role":"system","content":"Pick the highest-scoring legal Scrabble move..."}, {"role":"user","content":json.dumps({"rack":rack,"board":board})}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True, enable_thinking=False)out = model.generate(**tok(text, return_tensors="pt").to("cuda"), max_new_tokens=120, do_sample=False)print(tok.decode(out[0][tok(text, return_tensors="pt")["input_ids"].shape[1]:], skip_special_tokens=True))