Text Generation
Transformers
Safetensors
qwen3
dflash2
block-diffusion
speculative-decoding
draft-model
sglang
vllm
minicpm
text-generation-inference
Instructions to use applepie69/MiniCPM5-2B-DFlash2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use applepie69/MiniCPM5-2B-DFlash2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="applepie69/MiniCPM5-2B-DFlash2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("applepie69/MiniCPM5-2B-DFlash2") model = AutoModel.from_pretrained("applepie69/MiniCPM5-2B-DFlash2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use applepie69/MiniCPM5-2B-DFlash2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "applepie69/MiniCPM5-2B-DFlash2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "applepie69/MiniCPM5-2B-DFlash2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/applepie69/MiniCPM5-2B-DFlash2
- SGLang
How to use applepie69/MiniCPM5-2B-DFlash2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "applepie69/MiniCPM5-2B-DFlash2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "applepie69/MiniCPM5-2B-DFlash2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "applepie69/MiniCPM5-2B-DFlash2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "applepie69/MiniCPM5-2B-DFlash2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use applepie69/MiniCPM5-2B-DFlash2 with Docker Model Runner:
docker model run hf.co/applepie69/MiniCPM5-2B-DFlash2
DFlash2 drafter for openbmb/MiniCPM5-2B (overall 1.086x, coding 1.087x, agentic 1.109x, 4600 steps)
c93e263 verified Download dflash2_training_meta.json from applepie69/MiniCPM5-2B-DFlash2: direct link, hf CLI and curl.
- Browser
- Download file 9.02 kB
-
https://huggingface.co/applepie69/MiniCPM5-2B-DFlash2/resolve/main/dflash2_training_meta.json
- Command line
-
hf download hf://applepie69/MiniCPM5-2B-DFlash2/dflash2_training_meta.json
-
curl -L -o dflash2_training_meta.json https://huggingface.co/applepie69/MiniCPM5-2B-DFlash2/resolve/main/dflash2_training_meta.json
9.02 kB
| { | |
| "target": "openbmb/MiniCPM5-2B", | |
| "steps": 4600, | |
| "block_size": 8, | |
| "taps": [ | |
| 1, | |
| 10, | |
| 20, | |
| 30, | |
| 39 | |
| ], | |
| "mask_token_id": 75982, | |
| "num_blocks": 4, | |
| "seq_len": 1536, | |
| "data_mix_p1": [ | |
| "HuggingFaceH4/ultrachat_200k", | |
| "open-r1/OpenR1-Math-220k", | |
| "ise-uiuc/Magicoder-Evol-Instruct-110K", | |
| "HuggingFaceTB/smoltalk", | |
| "HuggingFaceFW/fineweb-edu" | |
| ], | |
| "data_mix_p2": [ | |
| "ise-uiuc/Magicoder-Evol-Instruct-110K", | |
| "HuggingFaceTB/smoltalk", | |
| "bigcode/self-oss-instruct-sc2-exec-filter-50k", | |
| "HuggingFaceH4/ultrachat_200k", | |
| "open-r1/OpenR1-Math-220k" | |
| ], | |
| "measured": { | |
| "domains": { | |
| "coding": { | |
| "n": 6, | |
| "plain_tok_s": 17.81, | |
| "spec_tok_s": 19.36, | |
| "speedup": 1.087, | |
| "acceptance_length": 1.234, | |
| "greedy_identical": "6/6", | |
| "per_prompt": [ | |
| { | |
| "prompt_tokens": 327, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.61, | |
| "spec_tok_s": 19.83, | |
| "speedup": 1.126, | |
| "al": 1.269, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 33, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.98, | |
| "spec_tok_s": 19.58, | |
| "speedup": 1.089, | |
| "al": 1.25, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 113, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.85, | |
| "spec_tok_s": 19.21, | |
| "speedup": 1.076, | |
| "al": 1.232, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 199, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.75, | |
| "spec_tok_s": 19.74, | |
| "speedup": 1.112, | |
| "al": 1.256, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 38, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.79, | |
| "spec_tok_s": 18.6, | |
| "speedup": 1.045, | |
| "al": 1.175, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 61, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.89, | |
| "spec_tok_s": 19.25, | |
| "speedup": 1.076, | |
| "al": 1.226, | |
| "identical": true | |
| } | |
| ], | |
| "raw": { | |
| "plain_tok": 1536, | |
| "plain_t": 86.24226474761963, | |
| "spec_tok": 1536, | |
| "spec_t": 79.34601759910583, | |
| "ident": 6, | |
| "n": 6, | |
| "al_sum": 1530.0, | |
| "al_n": 1240 | |
| }, | |
| "projected": 1.005 | |
| }, | |
| "agentic": { | |
| "n": 6, | |
| "plain_tok_s": 17.98, | |
| "spec_tok_s": 19.94, | |
| "speedup": 1.109, | |
| "acceptance_length": 1.267, | |
| "greedy_identical": "5/6", | |
| "per_prompt": [ | |
| { | |
| "prompt_tokens": 24, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.96, | |
| "spec_tok_s": 18.77, | |
| "speedup": 1.045, | |
| "al": 1.192, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 26, | |
| "new_tokens": 256, | |
| "plain_tok_s": 18.05, | |
| "spec_tok_s": 20.06, | |
| "speedup": 1.111, | |
| "al": 1.262, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 40, | |
| "new_tokens": 256, | |
| "plain_tok_s": 18.01, | |
| "spec_tok_s": 19.83, | |
| "speedup": 1.101, | |
| "al": 1.256, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 64, | |
| "new_tokens": 27, | |
| "plain_tok_s": 17.38, | |
| "spec_tok_s": 22.75, | |
| "speedup": 1.309, | |
| "al": 1.444, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 30, | |
| "new_tokens": 28, | |
| "plain_tok_s": 17.9, | |
| "spec_tok_s": 22.04, | |
| "speedup": 1.231, | |
| "al": 1.421, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 34, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.97, | |
| "spec_tok_s": 20.74, | |
| "speedup": 1.154, | |
| "al": 1.335, | |
| "identical": false | |
| } | |
| ], | |
| "raw": { | |
| "plain_tok": 1079, | |
| "plain_t": 60.022462368011475, | |
| "spec_tok": 1079, | |
| "spec_t": 54.1166627407074, | |
| "ident": 5, | |
| "n": 6, | |
| "al_sum": 1073.0, | |
| "al_n": 847 | |
| }, | |
| "projected": 1.032 | |
| }, | |
| "math": { | |
| "n": 6, | |
| "plain_tok_s": 17.91, | |
| "spec_tok_s": 19.28, | |
| "speedup": 1.076, | |
| "acceptance_length": 1.226, | |
| "greedy_identical": "5/6", | |
| "per_prompt": [ | |
| { | |
| "prompt_tokens": 71, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.93, | |
| "spec_tok_s": 17.57, | |
| "speedup": 0.98, | |
| "al": 1.118, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 35, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.83, | |
| "spec_tok_s": 19.91, | |
| "speedup": 1.116, | |
| "al": 1.269, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 58, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.93, | |
| "spec_tok_s": 19.47, | |
| "speedup": 1.086, | |
| "al": 1.25, | |
| "identical": false | |
| }, | |
| { | |
| "prompt_tokens": 43, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.8, | |
| "spec_tok_s": 19.72, | |
| "speedup": 1.108, | |
| "al": 1.256, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 116, | |
| "new_tokens": 256, | |
| "plain_tok_s": 18.0, | |
| "spec_tok_s": 20.6, | |
| "speedup": 1.144, | |
| "al": 1.301, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 61, | |
| "new_tokens": 256, | |
| "plain_tok_s": 18.0, | |
| "spec_tok_s": 18.69, | |
| "speedup": 1.038, | |
| "al": 1.181, | |
| "identical": true | |
| } | |
| ], | |
| "raw": { | |
| "plain_tok": 1536, | |
| "plain_t": 85.73986506462097, | |
| "spec_tok": 1536, | |
| "spec_t": 79.68685555458069, | |
| "ident": 5, | |
| "n": 6, | |
| "al_sum": 1530.0, | |
| "al_n": 1248 | |
| }, | |
| "projected": 0.998 | |
| }, | |
| "general": { | |
| "n": 6, | |
| "plain_tok_s": 17.9, | |
| "spec_tok_s": 19.26, | |
| "speedup": 1.076, | |
| "acceptance_length": 1.228, | |
| "greedy_identical": "5/6", | |
| "per_prompt": [ | |
| { | |
| "prompt_tokens": 66, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.92, | |
| "spec_tok_s": 20.38, | |
| "speedup": 1.137, | |
| "al": 1.294, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 99, | |
| "new_tokens": 256, | |
| "plain_tok_s": 18.02, | |
| "spec_tok_s": 20.12, | |
| "speedup": 1.116, | |
| "al": 1.269, | |
| "identical": false | |
| }, | |
| { | |
| "prompt_tokens": 143, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.96, | |
| "spec_tok_s": 19.69, | |
| "speedup": 1.096, | |
| "al": 1.244, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 330, | |
| "new_tokens": 106, | |
| "plain_tok_s": 17.81, | |
| "spec_tok_s": 18.36, | |
| "speedup": 1.03, | |
| "al": 1.193, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 93, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.79, | |
| "spec_tok_s": 18.64, | |
| "speedup": 1.048, | |
| "al": 1.192, | |
| "identical": true | |
| }, | |
| { | |
| "prompt_tokens": 106, | |
| "new_tokens": 256, | |
| "plain_tok_s": 17.82, | |
| "spec_tok_s": 18.08, | |
| "speedup": 1.014, | |
| "al": 1.164, | |
| "identical": true | |
| } | |
| ], | |
| "raw": { | |
| "plain_tok": 1386, | |
| "plain_t": 77.45153427124023, | |
| "spec_tok": 1386, | |
| "spec_t": 71.95891618728638, | |
| "ident": 5, | |
| "n": 6, | |
| "al_sum": 1380.0, | |
| "al_n": 1124 | |
| }, | |
| "projected": 1.0 | |
| } | |
| }, | |
| "overall": { | |
| "n": 24, | |
| "plain_tok_s": 17.89, | |
| "spec_tok_s": 19.42, | |
| "acceptance_length": 1.236, | |
| "greedy_identical": "21/24", | |
| "speedup": 1.086, | |
| "projected": 1.006 | |
| }, | |
| "costs": { | |
| "target_decode_ms": 57.714, | |
| "target_verify8_ms": 55.433, | |
| "draft_block_ms": 15.442 | |
| }, | |
| "gates_met": false, | |
| "steps_trained": 4600, | |
| "targets": { | |
| "coding": 2.0, | |
| "agentic": 2.0, | |
| "overall": 1.5 | |
| }, | |
| "device": "Tesla T4", | |
| "validation_mode": false | |
| } | |
| } |