|
--- |
|
license: apache-2.0 |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
- llama-cpp |
|
- gguf-my-repo |
|
- llama-factory |
|
base_model: martimfasantos/tinyllama-1.1b-chat-dpo-full |
|
datasets: |
|
- HuggingFaceH4/ultrafeedback_binarized |
|
model-index: |
|
- name: tinyllama-1.1b-chat-dpo-full |
|
results: [] |
|
--- |
|
|
|
# israellaguan/tinyllama-1.1b-chat-dpo-full-Q8_0-GGUF |
|
|
|
|
|
![llama.png](https://cdn-uploads.huggingface.co/production/uploads/65f70cf7f9e25ad18a609fdb/NLov4f5I1a4r8_AXgSzWj.png) |
|
This model was converted to GGUF format from [`martimfasantos/tinyllama-1.1b-chat-dpo-full`](https://huggingface.co/martimfasantos/tinyllama-1.1b-chat-dpo-full) 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/martimfasantos/tinyllama-1.1b-chat-dpo-full) 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 --hf-repo israellaguan/tinyllama-1.1b-chat-dpo-full-Q8_0-GGUF --hf-file tinyllama-1.1b-chat-dpo-full-q8_0.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo israellaguan/tinyllama-1.1b-chat-dpo-full-Q8_0-GGUF --hf-file tinyllama-1.1b-chat-dpo-full-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. |
|
``` |
|
./main --hf-repo israellaguan/tinyllama-1.1b-chat-dpo-full-Q8_0-GGUF --hf-file tinyllama-1.1b-chat-dpo-full-q8_0.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./server --hf-repo israellaguan/tinyllama-1.1b-chat-dpo-full-Q8_0-GGUF --hf-file tinyllama-1.1b-chat-dpo-full-q8_0.gguf -c 2048 |
|
``` |
|
|