Instructions to use iamplus/mpt-30b-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iamplus/mpt-30b-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="iamplus/mpt-30b-v3", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("iamplus/mpt-30b-v3", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("iamplus/mpt-30b-v3", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use iamplus/mpt-30b-v3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "iamplus/mpt-30b-v3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iamplus/mpt-30b-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/iamplus/mpt-30b-v3
- SGLang
How to use iamplus/mpt-30b-v3 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 "iamplus/mpt-30b-v3" \ --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": "iamplus/mpt-30b-v3", "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 "iamplus/mpt-30b-v3" \ --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": "iamplus/mpt-30b-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use iamplus/mpt-30b-v3 with Docker Model Runner:
docker model run hf.co/iamplus/mpt-30b-v3
Commit ·
9955fd1
1
Parent(s): 901d8d1
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,15 +4,15 @@ datasets:
|
|
| 4 |
license: apache-2.0
|
| 5 |
---
|
| 6 |
|
| 7 |
-
**Base Model :**
|
| 8 |
|
| 9 |
**Tool :** MosaicML's llm-foundry (https://github.com/mosaicml/llm-foundry)
|
| 10 |
|
| 11 |
**Dataset :** Entire flan1m-GPT4 dataset
|
| 12 |
|
| 13 |
-
**Config yaml with Model Params :** https://huggingface.co/
|
| 14 |
|
| 15 |
-
***Description :*** **mosaicml/mpt-30b** -> Finetuning on (Entire flan3m-GPT3.5 dataset for 1 epoch) -> **
|
| 16 |
|
| 17 |
**Prompt Format :**
|
| 18 |
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
---
|
| 6 |
|
| 7 |
+
**Base Model :** iamplus/mpt-30b-v2
|
| 8 |
|
| 9 |
**Tool :** MosaicML's llm-foundry (https://github.com/mosaicml/llm-foundry)
|
| 10 |
|
| 11 |
**Dataset :** Entire flan1m-GPT4 dataset
|
| 12 |
|
| 13 |
+
**Config yaml with Model Params :** https://huggingface.co/iamplus/mpt-30b-v3/blob/main/mpt-30b_orca.yaml
|
| 14 |
|
| 15 |
+
***Description :*** **mosaicml/mpt-30b** -> Finetuning on (Entire flan3m-GPT3.5 dataset for 1 epoch) -> **iamplus/mpt-30b-v2** -> Finetuning on (Entire flan1m-GPT4 dataset for 1 epoch) -> **iamplus/mpt-30b-v3**
|
| 16 |
|
| 17 |
**Prompt Format :**
|
| 18 |
|