openbmb/MiniCPM-V-4.7-35B-A3B-DSpark

MiniCPM-V-4.7-35B-A3B-DSpark

MiniCPM-V-4.7-35B-A3B-DSpark is a DSpark draft checkpoint trained for exact pairing with MiniCPM-V-4.7-35B-A3B and its tokenizer.

Model Specification

| Property | Value | | ----------------------------- | ----------------------------------------------------------------------------- | | Target model | MiniCPM-V-4.7-35B-A3B | | Draft layers | 5 | | Draft parameters | 389,223,169 | | Draft tokens per forward pass | 15 | | Target hidden-state layers | [3, 11, 19, 27, 35] | | Checkpoint precision | BF16 |

Training Recipe

Training responses were generated by MiniCPM-V-4.7-35B-A3B from a mixture of Vision & Text prompts.

| Setting | Value | | ------------------ | ------------------------- | | Training sequences | 2M | | Epochs | 6 | | Optimizer | AdamW | | Objective | CE + L1 + confidence loss |

Evaluation

Acceptance length is defined as the total number of completion tokens divided by the total number of speculative verification steps. Evaluation uses natural EOS termination and max_new_tokens=8192.

| Domain | Accept Length | | --------------------- | ----------------- | | Vision | | | MMMU | 5.098 | | MathVista | 6.126 | | CharXiv_reasoning_val | 5.479 | | OCRBench | 5.407 | | Text | | | Math | 6.687 | | Code | 7.387 | | General | 3.501 |

Usage with vLLM

vllm serve \
--model openbmb/MiniCPM-V-4.7-35B-A3B \
--served-model-name MiniCPM-V-4.7-35B-A3B \
--tensor-parallel-size 2 \
--max-model-len 40960 \
--max-num-batched-tokens 40960 \
--max-num-seqs 1 \
--attention-backend FLASH_ATTN \
--mm-encoder-attn-backend FLASH_ATTN \
--mm-processor-kwargs '{"downsample_mode":"4x"}' \
--trust-request-mm-kwargs \
--disable-custom-all-reduce \
--compilation-config '{"pass_config":{"fuse_allreduce_rms":false}}' \
--speculative-config '{"method":"dspark","model":"openbmb/MiniCPM-V-4.7-35B-A3B-DSpark","num_speculative_tokens":15,"enable_adaptive_verification":false}' \
--default-chat-template-kwargs '{"enable_thinking":false}'

Limitations and Disclaimer

This model has no autonomous intent or legal personhood; its outputs are text generated from statistical patterns and may be inaccurate, biased, or offensive, and may be manipulated by carefully crafted prompts ("jailbreaks") into producing unintended content. Its responses on sensitive topics such as politics, health, finance, and law are not reviewed by experts and should not be treated as professional advice.

This model is provided "AS IS", without warranty of any kind, express or implied, and the developers are not liable for any damages arising from its use. Users must employ the model only for lawful, compliant, and ethical purposes, configure their own safeguards, and label AI-generated content where required; deliberate jailbreaking, injection attacks, or inducing harmful output is prohibited, and any such testing is at the user's own risk.