Instructions to use itpossible/ClimateChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itpossible/ClimateChat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="itpossible/ClimateChat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("itpossible/ClimateChat")
model = AutoModelForCausalLM.from_pretrained("itpossible/ClimateChat", device_map="auto")
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 Settings

vLLM

How to use itpossible/ClimateChat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itpossible/ClimateChat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itpossible/ClimateChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/itpossible/ClimateChat

SGLang

How to use itpossible/ClimateChat 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/ClimateChat" \
    --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": "itpossible/ClimateChat",
		"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 "itpossible/ClimateChat" \
        --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": "itpossible/ClimateChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use itpossible/ClimateChat with Docker Model Runner:
```
docker model run hf.co/itpossible/ClimateChat
```

itpossible commited on Jan 14, 2025

Commit

2f51150

verified ·

1 Parent(s): c5c105e

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -1

README.md CHANGED Viewed

@@ -6,4 +6,31 @@ library_name: transformers
 tags:
 - text-generation-inference
 - inference endpoints
----

 tags:
 - text-generation-inference
 - inference endpoints
+---
+## 🎉 News
+- [2024-12-31] **Article [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 for publication in the *International Journal fo Digital Earth***. [Code and Data](https://github.com/THU-ESIS/JiuZhou).
+- [2024-10-11] WeChat article: [PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models](https://mp.weixin.qq.com/s/ugJQ9tbp6Y87xA3TOWteqw).
+- [2024-09-06] Released [ClimateChat](https://huggingface.co/itpossible/ClimateChat) instruct model.
+- [2024-08-31] **Article [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 for publication in the *Big Earth Data* journal**.
+- [2024-08-31] Released [Chinese-Mistral-7B-Instruct-v0.2](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2) instruct model. Significant improvements in language understanding and multi-turn dialogue capabilities.
+- [2024-06-30] Released [JiuZhou-Instruct-v0.2](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.2) instruct model. Significant improvements in language understanding and multi-turn dialogue capabilities.
+- [2024-05-15] WeChat Article: [Chinese Vocabulary Expansion Incremental Pretraining for Large Language Models: Chinese-Mistral Released](https://mp.weixin.qq.com/s/PMQmRCZMWosWMfgKRBjLlQ).
+- [2024-04-04] Released [Chinese-Mistral-7B-Instruct-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1) instruct model.
+- [2024-03-31] Released [Chinese-Mistral-7B-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B) base model.
+- [2024-03-15] Released the 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).
+## Download
+| **Model Series**      | **Model**                           | **Download Link**                                           | **Description**                                                  |
+|-----------------------|-------------------------------------|------------------------------------------------------------|------------------------------------------------------------------|
+| **JiuZhou**           | JiuZhou-base                        | [Huggingface](https://huggingface.co/itpossible/JiuZhou-base) | Base model (Rich in geoscience knowledge)                     |
+| **JiuZhou**           | JiuZhou-Instruct-v0.1               | [Huggingface](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1) | Instruct model (Instruction alignment caused a loss of some geoscience knowledge, but it has instruction-following ability) <br> LoRA fine-tuned on Alpaca_GPT4 in both Chinese and English and GeoSignal |
+| **JiuZhou**           | JiuZhou-Instruct-v0.2               | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.2) | Instruct model (Instruction alignment caused a loss of some geoscience knowledge, but it has instruction-following ability) <br> Fine-tuned with high-quality general instruction data |
+| **ClimateChat**       | ClimateChat                         | [HuggingFace](https://huggingface.co/itpossible/ClimateChat)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/ClimateChat) | Instruct model <br> Fine-tuned on JiuZhou-base for instruction following |
+| **Chinese-Mistral**   | Chinese-Mistral-7B                  | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-v0.1)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-v0.1)<br>[ModelScope](https://www.modelscope.cn/models/itpossible/Chinese-Mistral-7B-v0.1) | Base model                                                      |
+| **Chinese-Mistral**   | Chinese-Mistral-7B-Instruct-v0.1    | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.1)<br>[ModelScope](https://www.modelscope.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.1) | Instruct model <br> LoRA fine-tuned with Alpaca_GPT4 in both Chinese and English |
+| **Chinese-Mistral**   | Chinese-Mistral-7B-Instruct-v0.2    | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.2) | Instruct model <br> LoRA fine-tuned with a million high-quality instructions |
+| **PreparedLLM**       | Prepared-Llama                      | [Huggingface](https://huggingface.co/itpossible/Prepared-Llama)<br>[Wisemodel](https://wisemodel.cn/models/itpossible/PREPARED-Llama) | Base model <br> Continual pretraining with a small number of geoscience data <br> Recommended to use JiuZhou |