Instructions to use None1145/ChatGLM3-6B-Theresa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use None1145/ChatGLM3-6B-Theresa with Transformers:

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

pipe = pipeline("text-generation", model="None1145/ChatGLM3-6B-Theresa")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("None1145/ChatGLM3-6B-Theresa", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use None1145/ChatGLM3-6B-Theresa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "None1145/ChatGLM3-6B-Theresa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "None1145/ChatGLM3-6B-Theresa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/None1145/ChatGLM3-6B-Theresa

SGLang

How to use None1145/ChatGLM3-6B-Theresa 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 "None1145/ChatGLM3-6B-Theresa" \
    --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": "None1145/ChatGLM3-6B-Theresa",
		"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 "None1145/ChatGLM3-6B-Theresa" \
        --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": "None1145/ChatGLM3-6B-Theresa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use None1145/ChatGLM3-6B-Theresa with Docker Model Runner:
```
docker model run hf.co/None1145/ChatGLM3-6B-Theresa
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Configuration Parsing Warning:Config file config.json cannot be fetched (too big)

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

Model Introduction

These models are based on the text training of Theresa from Arknights

Chat

>>> from transformers import AutoTokenizer, AutoModel
>>> tokenizer = AutoTokenizer.from_pretrained("None1145/ChatGLM3-6B-Theresa", trust_remote_code=True)
>>> model = AutoModel.from_pretrained("None1145/ChatGLM3-6B-Theresa", trust_remote_code=True).half().cuda()
>>> system_prompt = "请扮演特蕾西娅"
>>> response, history = model.chat(tokenizer, "你好", history=[])
>>> print(response)
现在我们出去走走，好吗？
>>> response, history = model.chat(tokenizer, "好啊，特蕾西娅小姐", history=history)
>>> print(response)
让我们到那片小草地上看看吧，阿米娅。

Downloads last month: 23

Safetensors

Model size

6B params

Tensor type

F16

Model tree for None1145/ChatGLM3-6B-Theresa

Base model

zai-org/chatglm3-6b

Finetuned

(8)

this model

Quantizations

1 model

None1145
/

ChatGLM3-6B-Theresa

Model Introduction

Chat

Model tree for None1145/ChatGLM3-6B-Theresa

Dataset used to train None1145/ChatGLM3-6B-Theresa