GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Danny-Dasilva
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Danny-Dasilva
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Antidoom FTPO pass: sampled completions at temperature 0.01 from the
LiquidAI/antidoom-mix-v1.0 prompt mix
(filtered to the highest doom-loop-yield sources: code + instruction-following), detected runaway
repetition, extracted 156 FTPO preference pairs (105 after regularisation filtering), trained a LoRA (r=128, all layers + lm_head, max_seq 3072)
with early stop at chosen_win ≥ 0.4, and merged it into the base weights.
Post-training GPTQ (llm-compressor): int4 W4A16 group=32 symmetric, 256 ultrachat calibration samples with chat template. Post-training quantization preserves DSpark draft acceptance — retraining-style (QAT) quantization destroys it (see gemma-4-12B-it-W4A16-GPTQ-g32-DSpark).
DSpark acceptance is preserved through both steps: ~25% (original bf16) → 24.8% (after antidoom) → 26.1% (after GPTQ). The FTPO patch is local and targeted; it does not break the draft head.
| config | tok/s | DSpark accept |
|---|---|---|
| this model + DSpark k=7 + CUDA graphs | 341 (peaks 454) | 26.1% |
| this model, native (no speculation) | 224 | — |
| antidoom merged bf16 + DSpark k=7 | 188 | 24.8% |
python
from vllm import LLM, SamplingParamsfrom transformers import AutoTokenizer MODEL = "Danny-Dasilva/Qwen3-8B-antidoom-W4A16-GPTQ-g32-DSpark"DRAFT = "deepseek-ai/dspark_qwen3_8b_block7" llm = LLM( model=MODEL, max_model_len=8192, attention_backend="FLASHINFER", speculative_config={ "method": "dspark", "model": DRAFT, "num_speculative_tokens": 7, # draft block size; keep at 7 "attention_backend": "TRITON_ATTN", },)tok = AutoTokenizer.from_pretrained(MODEL)prompt = tok.apply_chat_template([{"role": "user", "content": "Hello!"}], add_generation_prompt=True, tokenize=False)print(llm.generate([prompt], SamplingParams(temperature=0.0, max_tokens=256))[0].outputs[0].text)Requires a vLLM build with DSpark support (merged to vLLM main 2026-07-02).
temperature=0.01, prompt sources filtered to code/instruction-following (3-8× higher loop yield
than math/QA), pair budget 156 (generation cut at ~5h; the chosen-win early stop converges regardless), num_epochs=3, lora_r=128, max_seq_length=3072 (fits 32 GB — the FTPO trainer materialises full-vocab logits), with the built-in chosen_win ≥ 0.4 early stop.Qwen/Qwen3-8B (bf16) → antidoom FTPO LoRA merge → GPTQ W4A16 g32from vllm import LLM, SamplingParamsfrom transformers import AutoTokenizer MODEL = "Danny-Dasilva/Qwen3-8B-antidoom-W4A16-GPTQ-g32-DSpark"DRAFT = "deepseek-ai/dspark_qwen3_8b_block7" llm = LLM( model=MODEL, max_model_len=8192, attention_backend="FLASHINFER", speculative_config={ "method": "dspark", "model": DRAFT, "num_speculative_tokens": 7, # draft block size; keep at 7 "attention_backend": "TRITON_ATTN", },)tok = AutoTokenizer.from_pretrained(MODEL)prompt = tok.apply_chat_template([{"role": "user", "content": "Hello!"}], add_generation_prompt=True, tokenize=False)print(llm.generate([prompt], SamplingParams(temperature=0.0, max_tokens=256))[0].outputs[0].text)