Instructions to use itpossible/JiuZhou-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use itpossible/JiuZhou-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="itpossible/JiuZhou-base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("itpossible/JiuZhou-base") model = AutoModelForCausalLM.from_pretrained("itpossible/JiuZhou-base") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use itpossible/JiuZhou-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "itpossible/JiuZhou-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "itpossible/JiuZhou-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/itpossible/JiuZhou-base
- SGLang
How to use itpossible/JiuZhou-base 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 "itpossible/JiuZhou-base" \ --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": "itpossible/JiuZhou-base", "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 "itpossible/JiuZhou-base" \ --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": "itpossible/JiuZhou-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use itpossible/JiuZhou-base with Docker Model Runner:
docker model run hf.co/itpossible/JiuZhou-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,16 +6,18 @@
|
|
| 6 |
|
| 7 |
|
| 8 |
## 🎉 News
|
| 9 |
-
- [
|
| 10 |
-
- [
|
| 11 |
-
- [
|
| 12 |
-
- [2024-
|
| 13 |
-
- [2024-
|
| 14 |
-
- [2024-
|
| 15 |
-
- [2024-
|
| 16 |
-
- [2024-
|
| 17 |
-
- [2024-
|
| 18 |
-
- [2024-03
|
|
|
|
|
|
|
| 19 |
|
| 20 |
|
| 21 |
## Table of Contents
|
|
|
|
| 6 |
|
| 7 |
|
| 8 |
## 🎉 News
|
| 9 |
+
- **[2025-05]** Paper [*TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks*](https://arxiv.org/abs/2506.12473) has been accepted by the top NLP conference *ACL*. [Model Download](https://huggingface.co/itpossible/TagGenerator).
|
| 10 |
+
- **[2025-03]** Paper [*GeoFactory: an LLM Performance Enhancement Framework for Geoscience Factual and Inferential Tasks*](https://www.tandfonline.com/doi/full/10.1080/20964471.2025.2506291) has been accepted by the journal *Big Earth Data*. [Data Download](https://huggingface.co/datasets/itpossible/WikiRAG).
|
| 11 |
+
- **[2025-03]** Paper [*ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries*](http://arxiv.org/abs/2506.13796) has been accepted by the International Conference on Learning Representations (*ICLR*). [Model Download](https://huggingface.co/itpossible/ClimateChat).
|
| 12 |
+
- **[2024-12]** Paper [*JiuZhou: Open Foundation Language Models and Effective Pre-training Framework for Geoscience*](https://www.tandfonline.com/doi/full/10.1080/17538947.2025.2449708) has been accepted by the *International Journal of Digital Earth*. [Model Introduction](https://deepwiki.com/THU-ESIS/JiuZhou). [Project Repository](https://github.com/THU-ESIS/JiuZhou).
|
| 13 |
+
- **[2024-09]** Released chat model [ClimateChat](https://huggingface.co/itpossible/ClimateChat).
|
| 14 |
+
- **[2024-08]** Paper [*PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models*](https://www.tandfonline.com/doi/full/10.1080/20964471.2024.2396159) has been accepted by the journal *Big Earth Data*. WeChat article: [PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models](https://mp.weixin.qq.com/s/ugJQ9tbp6Y87xA3TOWteqw). [Model Download](https://huggingface.co/itpossible/Prepared-Llama).
|
| 15 |
+
- **[2024-08]** Released chat model [Chinese-Mistral-7B-Instruct-v0.2](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2), featuring significantly improved language understanding and multi-turn conversation capabilities.
|
| 16 |
+
- **[2024-06]** Released chat model [JiuZhou-Instruct-v0.2](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.2), with significantly enhanced language understanding and multi-turn conversation capabilities.
|
| 17 |
+
- **[2024-05]** WeChat Article: [Chinese Vocabulary Expansion Incremental Pretraining for Large Language Models: Chinese-Mistral Released](https://mp.weixin.qq.com/s/PMQmRCZMWosWMfgKRBjLlQ).
|
| 18 |
+
- **[2024-03]** Released base model [Chinese-Mistral-7B-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B) and chat model [Chinese-Mistral-7B-Instruct-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1). [Model Introduction](https://deepwiki.com/THU-ESIS/Chinese-Mistral). [Project Repository](https://huggingface.co/itpossible/Chinese-Mistral).
|
| 19 |
+
- **[2024-03]** Released JiuZhou's base version [JiuZhou-base](https://huggingface.co/itpossible/JiuZhou-base), instruct version [JiuZhou-instruct-v0.1](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.1), and [intermediate checkpoints](https://huggingface.co/itpossible). [Model Introduction](https://deepwiki.com/THU-ESIS/JiuZhou). [Project Repository](https://github.com/THU-ESIS/JiuZhou).
|
| 20 |
+
- **[2024-01]** Completed training of Chinese-Mistral and JiuZhou, and commenced model evaluation.
|
| 21 |
|
| 22 |
|
| 23 |
## Table of Contents
|