Text Generation
Transformers
PyTorch
Japanese
mpt
Composer
MosaicML
llm-foundry
StreamingDatasets
mpt-7b
custom_code
text-generation-inference
Instructions to use Jumtra/mpt-7b-inst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jumtra/mpt-7b-inst with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jumtra/mpt-7b-inst", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jumtra/mpt-7b-inst", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Jumtra/mpt-7b-inst", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jumtra/mpt-7b-inst with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jumtra/mpt-7b-inst" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jumtra/mpt-7b-inst", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jumtra/mpt-7b-inst
- SGLang
How to use Jumtra/mpt-7b-inst 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 "Jumtra/mpt-7b-inst" \ --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": "Jumtra/mpt-7b-inst", "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 "Jumtra/mpt-7b-inst" \ --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": "Jumtra/mpt-7b-inst", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jumtra/mpt-7b-inst with Docker Model Runner:
docker model run hf.co/Jumtra/mpt-7b-inst
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,18 @@ June 28, 2023
|
|
| 28 |
|
| 29 |
CC-BY-SA-3.0
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## 使用方法
|
| 32 |
|
| 33 |
注意:このモデルでは、from_pretrainedメソッドにtrust_remote_code=Trueを渡す必要があります。
|
|
|
|
| 28 |
|
| 29 |
CC-BY-SA-3.0
|
| 30 |
|
| 31 |
+
## 評価
|
| 32 |
+
|
| 33 |
+
[Jumtra/test_data_100QA](https://huggingface.co/datasets/Jumtra/test_data_100QA)を用いてモデルの正答率を評価した
|
| 34 |
+
|
| 35 |
+
| model name | 正答率 |
|
| 36 |
+
| ---- | ---- |
|
| 37 |
+
| mosaicml/mpt-7b | 16/100 |
|
| 38 |
+
| mosaicml/mpt-7b-instruct | 28/100 |
|
| 39 |
+
| Jumtra/mpt-7b-base | 47/100 |
|
| 40 |
+
| Jumtra/mpt-7b-inst | 46/100 |
|
| 41 |
+
|
| 42 |
+
|
| 43 |
## 使用方法
|
| 44 |
|
| 45 |
注意:このモデルでは、from_pretrainedメソッドにtrust_remote_code=Trueを渡す必要があります。
|