GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
modrill
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
modrill
Model Tree
Qwen/Qwen3-8B-Base
Input Modalities
Output Modalities
Supported Functionality
| Student | Qwen/Qwen3-8B-Base revision 49e3418fbbbca6ecbdf9608b4d22e5a407081db4 |
| Teacher | Qwen/Qwen3-30B-A3B-Thinking-2507 traces (V4 paired think payload) |
| Problems | 4715 unique problems (source_1ep_rows); physical 2-epoch concat = 9430 rows |
| Dose | 32,436,894 assistant tokens / epoch; endpoint 64,873,788 assistant tokens (2 epochs) |
| Train seed | 42 |
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projlm_head frozen except two-sided trainable B-rows for 151643 (<|endoftext|>), 151667 (<think>), 151668 (</think>). Token ids from adapter/TOKEN_ROWS_META.json.<|endoftext|> (151643)Merged weights are the 2-epoch endpoint (step-000921, 64,873,788 assistant tokens). LoRA + B-rows are under adapter/.
256-problem LiveCodeBench-derived dev split. Seed 3407, think mode, no <think> prefill, max generation ~32k, sandbox-verified pass@1. Temperature 0.6, top-p 0.95, top-k 20.
Cap = generations that hit the 32k length limit without closing </think>.
| Model | pass@1 | Cap | Notes |
|---|---|---|---|
| CodeThink-V4-Qwen3-8B | 81/256 | 130 | this repo; seed 3407; V4 think contract |
| Qwen3-8B-Base | 55/256 | — | old-contract historical bare-base number (not a same-contract V4 think-mode re-eval; a same-contract 8B-base think COMPLETE.json was not on disk) |
Single seed. These are research checkpoints, not product scores.
For context, the same-family 4B base on the current V4 think contract is 63/256 (seed 3407), with a 5-seed band 55.2 ± 4.9 on an earlier bare-base protocol.
Merged full weights; no PEFT required at inference. Think mode: enable_thinking=True, do not prefill <think>.
python
from transformers import AutoModelForCausalLM, AutoTokenizerrepo = "modrill/CodeThink-V4-Qwen3-8B"tokenizer = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16", device_map="auto")system = ("You are an expert Python programmer. You will be given a question ""(problem specification) and will generate a correct Python program that ""matches the specification and passes all tests. You will NOT return ""anything except for the program.")messages = [{"role": "system", "content": system},{"role": "user", "content": problem_statement},]prompt = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=True,)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate(**inputs,max_new_tokens=32768,do_sample=True,temperature=0.6,top_p=0.95,top_k=20,)print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
Stop ids used in the official eval: 151643 (<|endoftext|>), 151645 (<|im_end|>).
OFFICIAL_MERGE_RECEIPT.jsonadapter/: LoRA, token_rows_both_sides.safetensors, TOKEN_ROWS_META.json, checkpoint MANIFEST.jsonprovenance/: train RUN_IDENTITY.json, TRAINING_CONFIG.json, POLICY.json; DEV256 COMPLETE.jsonMANIFEST.sha256Optimizer / resume states are not included.