71 lines
2.2 KiB
Markdown
71 lines
2.2 KiB
Markdown
---
|
|
license: other
|
|
license_name: license.md
|
|
license_link: https://huggingface.co/stabilityai/stablelm-zephyr-3b/blob/main/LICENSE.md
|
|
base_model: ChiKoi7/stablelm-zephyr-3b-Heretic
|
|
tags:
|
|
- Zephyr
|
|
- stablelm
|
|
- 3b
|
|
- stabilityai
|
|
- Heretic
|
|
- Uncensored
|
|
- Abliterated
|
|
- llama-cpp
|
|
- gguf-my-repo
|
|
datasets:
|
|
- HuggingFaceH4/ultrachat_200k
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
- meta-math/MetaMathQA
|
|
- WizardLMTeam/WizardLM_evol_instruct_V2_196k
|
|
- Intel/orca_dpo_pairs
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
---
|
|
|
|
# PJRM/stablelm-zephyr-3b-Heretic-Q4_0-GGUF
|
|
This model was converted to GGUF format from [`ChiKoi7/stablelm-zephyr-3b-Heretic`](https://huggingface.co/ChiKoi7/stablelm-zephyr-3b-Heretic) 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/ChiKoi7/stablelm-zephyr-3b-Heretic) for more details on the model.
|
|
|
|
## 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 PJRM/stablelm-zephyr-3b-Heretic-Q4_0-GGUF --hf-file stablelm-zephyr-3b-heretic-q4_0.gguf -p "The meaning to life and the universe is"
|
|
```
|
|
|
|
### Server:
|
|
```bash
|
|
llama-server --hf-repo PJRM/stablelm-zephyr-3b-Heretic-Q4_0-GGUF --hf-file stablelm-zephyr-3b-heretic-q4_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 PJRM/stablelm-zephyr-3b-Heretic-Q4_0-GGUF --hf-file stablelm-zephyr-3b-heretic-q4_0.gguf -p "The meaning to life and the universe is"
|
|
```
|
|
or
|
|
```
|
|
./llama-server --hf-repo PJRM/stablelm-zephyr-3b-Heretic-Q4_0-GGUF --hf-file stablelm-zephyr-3b-heretic-q4_0.gguf -c 2048
|
|
```
|