DavidAU's picture
Upload README.md with huggingface_hub
e734670 verified
---
license: apache-2.0
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
base_model:
- NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_3_V1
- cognitivecomputations/TinyDolphin-2.8-1.1b
- NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_1_V1
- NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_2_V1
widget:
- text: '<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
podrias escribir un codigo de ejemplo en Python<|im_end|>
<|im_start|>assistant
'
---
# DavidAU/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2-Q8_0-GGUF
This model was converted to GGUF format from [`NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2`](https://huggingface.co/NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2) 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/NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2-Q8_0-GGUF --model tinydolphin-2.8-1.1b_oasst2_chatml_all_cluster_dare_ties_v2.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyDolphin-2.8-1.1b_oasst2_chatML_all_Cluster_dare_ties_v2-Q8_0-GGUF --model tinydolphin-2.8-1.1b_oasst2_chatml_all_cluster_dare_ties_v2.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.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinydolphin-2.8-1.1b_oasst2_chatml_all_cluster_dare_ties_v2.Q8_0.gguf -n 128
```