Downloads · 30 days
0
chatglm3-6b-32k-fp16
npc0/chatglm3-6b-32k-fp16
chatglm3-6b-32k-fp16 is a machine learning model from npc0. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
介绍 (Introduction) ChatGLM3-6B-32k 是 ChatGLM 系列最新一代的开源模型，THUDM/chatglm3-6b
Access
Public
Updated Dec 24, 2023
Repo size
12.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin12.5 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 27, 2023
- Updated
- Dec 24, 2023
- SHA
- b61ad274
Model card
From the Hugging Face model README
ChatGLM3-6B-32k-fp16
介绍 (Introduction) ChatGLM3-6B-32k 是 ChatGLM 系列最新一代的开源模型，THUDM/chatglm3-6b
用 ChatGLM.CPP 基於 GGML quantize 生成 f16 權重 weights 儲存於此倉庫。
Performance
| Model | GGML quantize method | HDD size |
|---|---|---|
| chatglm3-32k-ggml-q4_0.bin | f16 | 12.5 GB |
Getting Started
- Install dependency
pip install chatglm-cpp transformers
- Download weight
wget https://huggingface.co/npc0/chatglm3-6b-32k-fp16/resolve/main/chatglm3-32k-ggml-f16.bin
- Code
import chatglm_cpp
pipeline = chatglm_cpp.Pipeline("./chatglm3-32k-ggml-f16.bin")
pipeline.chat([chatglm_cpp.ChatMessage(role="user", content="你好")])
# Output: ChatMessage(role="assistant", content="你好👋！我是人工智能助手 ChatGLM-6B，很高兴见到你，欢迎问我任何问题。", tool_calls=[])
- Languages
- zh, en
- Created
- Nov 27, 2023
- Updated
- Dec 24, 2023