|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
# THUDM's chatglm 6B GGML |
|
|
|
These files are GGML format model files for [THUDM's chatglm 6B](https://huggingface.co/THUDM/chatglm-6b). |
|
|
|
GGML files are for CPU + GPU inference using [chatglm.cpp](https://github.com/li-plus/chatglm.cpp) and [Xorbits Inference](https://github.com/xorbitsai/inference). |
|
|
|
# Prompt template |
|
**NOTE**: prompt template is not available yet since the system prompt is hard coded in chatglm.cpp for now. |
|
|
|
# Provided files |
|
|
|
| Name | Quant method | Bits | Size | |
|
|------|--------------|------|------| |
|
| chatglm-ggml-q4_0.bin | q4_0 | 4 | 3.5 GB | |
|
| chatglm-ggml-q4_1.bin | q4_1 | 4 | 3.9 GB | |
|
| chatglm-ggml-q5_0.bin | q5_0 | 5 | 4.3 GB | |
|
| chatglm-ggml-q5_1.bin | q5_1 | 5 | 4.6 GB | |
|
| chatglm-ggml-q5_1.bin | q8_0 | 8 | 6.6 GB | |
|
|
|
|
|
# How to run in Xorbits Inference |
|
|
|
## Install |
|
Xinference can be installed via pip from PyPI. It is highly recommended to create a new virtual environment to avoid conflicts. |
|
|
|
```bash |
|
$ pip install "xinference[all]" |
|
$ pip install chatglm-cpp |
|
``` |
|
|
|
## Start Xorbits Inference |
|
To start a local instance of Xinference, run the following command: |
|
```bash |
|
$ xinference |
|
``` |
|
|
|
Once Xinference is running, an endpoint will be accessible for model management via CLI or Xinference client. The default endpoint is `http://localhost:9997`. You can also view a web UI using the Xinference endpoint to chat with all the builtin models. You can even chat with two cutting-edge AI models side-by-side to compare their performance! |
|
|
|
 |
|
|
|
|
|
# Slack |
|
For further support, and discussions on these models and AI in general, join our [slack channel](https://join.slack.com/t/xorbitsio/shared_invite/zt-1o3z9ucdh-RbfhbPVpx7prOVdM1CAuxg)! |
|
|
|
# Original model card: THUDM's chatglm 6B |
|
ChatGLM-6B is an open bilingual language model based on General Language Model (GLM) framework, with 6.2 billion parameters. With the quantization technique, users can deploy locally on consumer-grade graphics cards (only 6GB of GPU memory is required at the INT4 quantization level). ChatGLM-6B uses technology similar to ChatGPT, optimized for Chinese QA and dialogue. The model is trained for about 1T tokens of Chinese and English corpus, supplemented by supervised fine-tuning, feedback bootstrap, and reinforcement learning with human feedback. With only about 6.2 billion parameters, the model is able to generate answers that are in line with human preference. |
|
|
|
For more instructions, including how to run CLI and web demos, and model quantization, please refer to our [Github Repo](https://github.com/THUDM/ChatGLM-6B). |
|
|
