Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
fp8
Instructions to use microsoft/MAI-DS-R1-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/MAI-DS-R1-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/MAI-DS-R1-FP8", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/MAI-DS-R1-FP8", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("microsoft/MAI-DS-R1-FP8", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/MAI-DS-R1-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/MAI-DS-R1-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/MAI-DS-R1-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/microsoft/MAI-DS-R1-FP8
- SGLang
How to use microsoft/MAI-DS-R1-FP8 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 "microsoft/MAI-DS-R1-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/MAI-DS-R1-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "microsoft/MAI-DS-R1-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/MAI-DS-R1-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use microsoft/MAI-DS-R1-FP8 with Docker Model Runner:
docker model run hf.co/microsoft/MAI-DS-R1-FP8
Delete git_add_safetensors.sh
Browse files- git_add_safetensors.sh +0 -174
git_add_safetensors.sh
DELETED
|
@@ -1,174 +0,0 @@
|
|
| 1 |
-
git add model-00001-of-000163.safetensors
|
| 2 |
-
git add model-00002-of-000163.safetensors
|
| 3 |
-
git add model-00003-of-000163.safetensors
|
| 4 |
-
git add model-00004-of-000163.safetensors
|
| 5 |
-
git add model-00005-of-000163.safetensors
|
| 6 |
-
git add model-00006-of-000163.safetensors
|
| 7 |
-
git add model-00007-of-000163.safetensors
|
| 8 |
-
git add model-00008-of-000163.safetensors
|
| 9 |
-
git add model-00009-of-000163.safetensors
|
| 10 |
-
git add model-00010-of-000163.safetensors
|
| 11 |
-
git add model-00011-of-000163.safetensors
|
| 12 |
-
git add model-00012-of-000163.safetensors
|
| 13 |
-
git add model-00013-of-000163.safetensors
|
| 14 |
-
git add model-00014-of-000163.safetensors
|
| 15 |
-
git add model-00015-of-000163.safetensors
|
| 16 |
-
git add model-00016-of-000163.safetensors
|
| 17 |
-
git add model-00017-of-000163.safetensors
|
| 18 |
-
git add model-00018-of-000163.safetensors
|
| 19 |
-
git add model-00019-of-000163.safetensors
|
| 20 |
-
git add model-00020-of-000163.safetensors
|
| 21 |
-
git add model-00021-of-000163.safetensors
|
| 22 |
-
git add model-00022-of-000163.safetensors
|
| 23 |
-
git add model-00023-of-000163.safetensors
|
| 24 |
-
git add model-00024-of-000163.safetensors
|
| 25 |
-
git add model-00025-of-000163.safetensors
|
| 26 |
-
git add model-00026-of-000163.safetensors
|
| 27 |
-
echo 'processed 25 files'
|
| 28 |
-
git add model-00027-of-000163.safetensors
|
| 29 |
-
git add model-00028-of-000163.safetensors
|
| 30 |
-
git add model-00029-of-000163.safetensors
|
| 31 |
-
git add model-00030-of-000163.safetensors
|
| 32 |
-
git add model-00031-of-000163.safetensors
|
| 33 |
-
git add model-00032-of-000163.safetensors
|
| 34 |
-
git add model-00033-of-000163.safetensors
|
| 35 |
-
git add model-00034-of-000163.safetensors
|
| 36 |
-
git add model-00035-of-000163.safetensors
|
| 37 |
-
git add model-00036-of-000163.safetensors
|
| 38 |
-
git add model-00037-of-000163.safetensors
|
| 39 |
-
git add model-00038-of-000163.safetensors
|
| 40 |
-
git add model-00039-of-000163.safetensors
|
| 41 |
-
git add model-00040-of-000163.safetensors
|
| 42 |
-
git add model-00041-of-000163.safetensors
|
| 43 |
-
git add model-00042-of-000163.safetensors
|
| 44 |
-
git add model-00043-of-000163.safetensors
|
| 45 |
-
git add model-00044-of-000163.safetensors
|
| 46 |
-
git add model-00045-of-000163.safetensors
|
| 47 |
-
git add model-00046-of-000163.safetensors
|
| 48 |
-
git add model-00047-of-000163.safetensors
|
| 49 |
-
git add model-00048-of-000163.safetensors
|
| 50 |
-
git add model-00049-of-000163.safetensors
|
| 51 |
-
git add model-00050-of-000163.safetensors
|
| 52 |
-
git add model-00051-of-000163.safetensors
|
| 53 |
-
echo 'processed 50 files'
|
| 54 |
-
git add model-00052-of-000163.safetensors
|
| 55 |
-
git add model-00053-of-000163.safetensors
|
| 56 |
-
git add model-00054-of-000163.safetensors
|
| 57 |
-
git add model-00055-of-000163.safetensors
|
| 58 |
-
git add model-00056-of-000163.safetensors
|
| 59 |
-
git add model-00057-of-000163.safetensors
|
| 60 |
-
git add model-00058-of-000163.safetensors
|
| 61 |
-
git add model-00059-of-000163.safetensors
|
| 62 |
-
git add model-00060-of-000163.safetensors
|
| 63 |
-
git add model-00061-of-000163.safetensors
|
| 64 |
-
git add model-00062-of-000163.safetensors
|
| 65 |
-
git add model-00063-of-000163.safetensors
|
| 66 |
-
git add model-00064-of-000163.safetensors
|
| 67 |
-
git add model-00065-of-000163.safetensors
|
| 68 |
-
git add model-00066-of-000163.safetensors
|
| 69 |
-
git add model-00067-of-000163.safetensors
|
| 70 |
-
git add model-00068-of-000163.safetensors
|
| 71 |
-
git add model-00069-of-000163.safetensors
|
| 72 |
-
git add model-00070-of-000163.safetensors
|
| 73 |
-
git add model-00071-of-000163.safetensors
|
| 74 |
-
git add model-00072-of-000163.safetensors
|
| 75 |
-
git add model-00073-of-000163.safetensors
|
| 76 |
-
git add model-00074-of-000163.safetensors
|
| 77 |
-
git add model-00075-of-000163.safetensors
|
| 78 |
-
git add model-00076-of-000163.safetensors
|
| 79 |
-
echo 'processed 75 files'
|
| 80 |
-
git add model-00077-of-000163.safetensors
|
| 81 |
-
git add model-00078-of-000163.safetensors
|
| 82 |
-
git add model-00079-of-000163.safetensors
|
| 83 |
-
git add model-00080-of-000163.safetensors
|
| 84 |
-
git add model-00081-of-000163.safetensors
|
| 85 |
-
git add model-00082-of-000163.safetensors
|
| 86 |
-
git add model-00083-of-000163.safetensors
|
| 87 |
-
git add model-00084-of-000163.safetensors
|
| 88 |
-
git add model-00085-of-000163.safetensors
|
| 89 |
-
git add model-00086-of-000163.safetensors
|
| 90 |
-
git add model-00087-of-000163.safetensors
|
| 91 |
-
git add model-00088-of-000163.safetensors
|
| 92 |
-
git add model-00089-of-000163.safetensors
|
| 93 |
-
git add model-00090-of-000163.safetensors
|
| 94 |
-
git add model-00091-of-000163.safetensors
|
| 95 |
-
git add model-00092-of-000163.safetensors
|
| 96 |
-
git add model-00093-of-000163.safetensors
|
| 97 |
-
git add model-00094-of-000163.safetensors
|
| 98 |
-
git add model-00095-of-000163.safetensors
|
| 99 |
-
git add model-00096-of-000163.safetensors
|
| 100 |
-
git add model-00097-of-000163.safetensors
|
| 101 |
-
git add model-00098-of-000163.safetensors
|
| 102 |
-
git add model-00099-of-000163.safetensors
|
| 103 |
-
git add model-00100-of-000163.safetensors
|
| 104 |
-
git add model-00101-of-000163.safetensors
|
| 105 |
-
echo 'processed 100 files'
|
| 106 |
-
git add model-00102-of-000163.safetensors
|
| 107 |
-
git add model-00103-of-000163.safetensors
|
| 108 |
-
git add model-00104-of-000163.safetensors
|
| 109 |
-
git add model-00105-of-000163.safetensors
|
| 110 |
-
git add model-00106-of-000163.safetensors
|
| 111 |
-
git add model-00107-of-000163.safetensors
|
| 112 |
-
git add model-00108-of-000163.safetensors
|
| 113 |
-
git add model-00109-of-000163.safetensors
|
| 114 |
-
git add model-00110-of-000163.safetensors
|
| 115 |
-
git add model-00111-of-000163.safetensors
|
| 116 |
-
git add model-00112-of-000163.safetensors
|
| 117 |
-
git add model-00113-of-000163.safetensors
|
| 118 |
-
git add model-00114-of-000163.safetensors
|
| 119 |
-
git add model-00115-of-000163.safetensors
|
| 120 |
-
git add model-00116-of-000163.safetensors
|
| 121 |
-
git add model-00117-of-000163.safetensors
|
| 122 |
-
git add model-00118-of-000163.safetensors
|
| 123 |
-
git add model-00119-of-000163.safetensors
|
| 124 |
-
git add model-00120-of-000163.safetensors
|
| 125 |
-
git add model-00121-of-000163.safetensors
|
| 126 |
-
git add model-00122-of-000163.safetensors
|
| 127 |
-
git add model-00123-of-000163.safetensors
|
| 128 |
-
git add model-00124-of-000163.safetensors
|
| 129 |
-
git add model-00125-of-000163.safetensors
|
| 130 |
-
git add model-00126-of-000163.safetensors
|
| 131 |
-
echo 'processed 125 files'
|
| 132 |
-
git add model-00127-of-000163.safetensors
|
| 133 |
-
git add model-00128-of-000163.safetensors
|
| 134 |
-
git add model-00129-of-000163.safetensors
|
| 135 |
-
git add model-00130-of-000163.safetensors
|
| 136 |
-
git add model-00131-of-000163.safetensors
|
| 137 |
-
git add model-00132-of-000163.safetensors
|
| 138 |
-
git add model-00133-of-000163.safetensors
|
| 139 |
-
git add model-00134-of-000163.safetensors
|
| 140 |
-
git add model-00135-of-000163.safetensors
|
| 141 |
-
git add model-00136-of-000163.safetensors
|
| 142 |
-
git add model-00137-of-000163.safetensors
|
| 143 |
-
git add model-00138-of-000163.safetensors
|
| 144 |
-
git add model-00139-of-000163.safetensors
|
| 145 |
-
git add model-00140-of-000163.safetensors
|
| 146 |
-
git add model-00141-of-000163.safetensors
|
| 147 |
-
git add model-00142-of-000163.safetensors
|
| 148 |
-
git add model-00143-of-000163.safetensors
|
| 149 |
-
git add model-00144-of-000163.safetensors
|
| 150 |
-
git add model-00145-of-000163.safetensors
|
| 151 |
-
git add model-00146-of-000163.safetensors
|
| 152 |
-
git add model-00147-of-000163.safetensors
|
| 153 |
-
git add model-00148-of-000163.safetensors
|
| 154 |
-
git add model-00149-of-000163.safetensors
|
| 155 |
-
git add model-00150-of-000163.safetensors
|
| 156 |
-
git add model-00151-of-000163.safetensors
|
| 157 |
-
echo 'processed 150 files'
|
| 158 |
-
git add model-00152-of-000163.safetensors
|
| 159 |
-
git add model-00153-of-000163.safetensors
|
| 160 |
-
git add model-00154-of-000163.safetensors
|
| 161 |
-
git add model-00155-of-000163.safetensors
|
| 162 |
-
git add model-00156-of-000163.safetensors
|
| 163 |
-
git add model-00157-of-000163.safetensors
|
| 164 |
-
git add model-00158-of-000163.safetensors
|
| 165 |
-
git add model-00159-of-000163.safetensors
|
| 166 |
-
git add model-00160-of-000163.safetensors
|
| 167 |
-
git add model-00161-of-000163.safetensors
|
| 168 |
-
git add model-00162-of-000163.safetensors
|
| 169 |
-
git add model-00163-of-000163.safetensors
|
| 170 |
-
git add *.py
|
| 171 |
-
git add *.json
|
| 172 |
-
git add *.md
|
| 173 |
-
git commit -m 'Add model files for fp8 model'
|
| 174 |
-
git push origin main
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|