|
|
--- |
|
|
base_model: THUDM/GLM-Z1-32B-0414 |
|
|
language: |
|
|
- zh |
|
|
- en |
|
|
library_name: transformers |
|
|
license: mit |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
--- |
|
|
|
|
|
# Triangle104/GLM-Z1-32B-0414-Q8_0-GGUF |
|
|
This model was converted to GGUF format from [`THUDM/GLM-Z1-32B-0414`](https://huggingface.co/THUDM/GLM-Z1-32B-0414) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
|
Refer to the [original model card](https://huggingface.co/THUDM/GLM-Z1-32B-0414) for more details on the model. |
|
|
|
|
|
--- |
|
|
The GLM family welcomes a new generation of open-source models, the GLM-4-32B-0414 |
|
|
series, featuring 32 billion parameters. Its performance is comparable |
|
|
to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very |
|
|
user-friendly local deployment features. GLM-4-32B-Base-0414 was |
|
|
pre-trained on 15T of high-quality data, including a large amount of |
|
|
reasoning-type synthetic data, laying the foundation for subsequent |
|
|
reinforcement learning extensions. In the post-training stage, in |
|
|
addition to human preference alignment for dialogue scenarios, we also |
|
|
enhanced the model's performance in instruction following, engineering |
|
|
code, and function calling using techniques such as rejection sampling |
|
|
and reinforcement learning, strengthening the atomic capabilities |
|
|
required for agent tasks. GLM-4-32B-0414 achieves good results in areas |
|
|
such as engineering code, Artifact generation, function calling, |
|
|
search-based Q&A, and report generation. Some benchmarks even rival |
|
|
larger models like GPT-4o and DeepSeek-V3-0324 (671B). |
|
|
|
|
|
GLM-Z1-32B-0414 is a reasoning model with deep thinking capabilities. |
|
|
This was developed based on GLM-4-32B-0414 through cold start and |
|
|
extended reinforcement learning, as well as further training of the |
|
|
model on tasks involving mathematics, code, and logic. Compared to the |
|
|
base model, GLM-Z1-32B-0414 significantly improves mathematical |
|
|
abilities and the capability to solve complex tasks. During the training |
|
|
process, we also introduced general reinforcement learning based on |
|
|
pairwise ranking feedback, further enhancing the model's general |
|
|
capabilities. |
|
|
|
|
|
--- |
|
|
## Use with llama.cpp |
|
|
Install llama.cpp through brew (works on Mac and Linux) |
|
|
|
|
|
```bash |
|
|
brew install llama.cpp |
|
|
|
|
|
``` |
|
|
Invoke the llama.cpp server or the CLI. |
|
|
|
|
|
### CLI: |
|
|
```bash |
|
|
llama-cli --hf-repo Triangle104/GLM-Z1-32B-0414-Q8_0-GGUF --hf-file glm-z1-32b-0414-q8_0.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/GLM-Z1-32B-0414-Q8_0-GGUF --hf-file glm-z1-32b-0414-q8_0.gguf -c 2048 |
|
|
``` |
|
|
|
|
|
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. |
|
|
|
|
|
Step 1: Clone llama.cpp from GitHub. |
|
|
``` |
|
|
git clone https://github.com/ggerganov/llama.cpp |
|
|
``` |
|
|
|
|
|
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). |
|
|
``` |
|
|
cd llama.cpp && LLAMA_CURL=1 make |
|
|
``` |
|
|
|
|
|
Step 3: Run inference through the main binary. |
|
|
``` |
|
|
./llama-cli --hf-repo Triangle104/GLM-Z1-32B-0414-Q8_0-GGUF --hf-file glm-z1-32b-0414-q8_0.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/GLM-Z1-32B-0414-Q8_0-GGUF --hf-file glm-z1-32b-0414-q8_0.gguf -c 2048 |
|
|
``` |
|
|
|
