code-think-q8b-20260908
Research checkpoint: Qwen/Qwen3-8B-Base (49e3418fbbbca6ecbdf9608b4d22e5a407081db4) after V4 LoRA SFT on Qwen3-30B-A3B-Thinking-2507 traces, then merged to full weights.
This is a research checkpoint, not a product. Single-seed diagnostic numbers only. Do not treat DEV256 as a leaderboard claim.
License: Apache-2.0, inherited from Qwen/Qwen3-8B-Base (verified from the local base README.md; Apache-2.0 text bundled from the Qwen3-4B-Base LICENSE file on disk).
Base, teacher, and data
| 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 |
Recipe
- LoRA r64 / α128, dropout 0.0, seven projections:
q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj - Embeddings /
lm_headfrozen except two-sided trainable B-rows for 151643 (<|endoftext|>), 151667 (<think>), 151668 (</think>). Token ids fromadapter/TOKEN_ROWS_META.json. - Assistant supervised tail:
<|endoftext|>(151643) - LR 1e-4, AdamW (β 0.9/0.95), cosine over assistant-token dose, warmup 6% (3,892,427 / 64,873,788 tokens), weight decay 0.1
- bf16, no packing, no truncation, context 32768
- 2 epochs, physical concat. Endpoint-only score; no checkpoint picking.
Merged weights are the 2-epoch endpoint (step-000921, 64,873,788 assistant tokens). LoRA + B-rows are under adapter/.
Evaluation (DEV256)
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 |
|---|---|---|---|
| code-think-q8b-20260908 | 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.
Usage
Merged full weights; no PEFT required at inference. Think mode: enable_thinking=True, do not prefill <think>.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "modrill/code-think-q8b-20260908"
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|>).
Repo layout
- Root: merged HF weights plus
OFFICIAL_MERGE_RECEIPT.json adapter/: LoRA,token_rows_both_sides.safetensors,TOKEN_ROWS_META.json, checkpointMANIFEST.jsonprovenance/: trainRUN_IDENTITY.json,TRAINING_CONFIG.json,POLICY.json; DEV256COMPLETE.jsonMANIFEST.sha256
Optimizer / resume states are not included.