|
|
--- |
|
|
base_model: DavidAU/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
--- |
|
|
|
|
|
# Triangle104/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B-Q4_K_M-GGUF |
|
|
This model was converted to GGUF format from [`DavidAU/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B`](https://huggingface.co/DavidAU/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B) 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/DavidAU/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B) for more details on the model. |
|
|
|
|
|
--- |
|
|
This model was converted to Nvidia's new "UltraLong8B" long context Llama 3.1 model structure (https://huggingface.co/nvidia/Llama-3.1-8B-UltraLong-1M-Instruct) |
|
|
which allowed full transfer of "Dark Planet 8B" in all it's "glory" so |
|
|
to speak. Due to Nvidia's structure, the new Dark Planet has attained |
|
|
far greater long generation not only |
|
|
in terms of context, but also coherence too. There is a also a bump in |
|
|
overall performance as well. |
|
|
|
|
|
This model has been designed to be relatively bullet proof and |
|
|
operates with all parameters, including temp settings from 0 to 5. |
|
|
|
|
|
It is an extraordinary compressed model, with a very low perplexity level (lower than Meta Llama3 Instruct). |
|
|
|
|
|
It is for any writing, fiction or roleplay activity. |
|
|
|
|
|
It requires Llama 3 template and/or "Command-R" template. |
|
|
|
|
|
Suggest a context window of at least 8k, 16K is better... as this model will generate long outputs unless you set a hard limit. |
|
|
|
|
|
Likewise, as this is an instruct model - the more instructions in |
|
|
your prompt and/or system prompt - the greater the output quality. |
|
|
|
|
|
IE: Less "guessing" equals far higher quality. |
|
|
|
|
|
--- |
|
|
## 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/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B-Q4_K_M-GGUF --hf-file llama-3.1-1million-ctx-dark-planet-v1.01-8b-q4_k_m.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B-Q4_K_M-GGUF --hf-file llama-3.1-1million-ctx-dark-planet-v1.01-8b-q4_k_m.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/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B-Q4_K_M-GGUF --hf-file llama-3.1-1million-ctx-dark-planet-v1.01-8b-q4_k_m.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/Llama-3.1-1million-ctx-Dark-Planet-v1.01-8B-Q4_K_M-GGUF --hf-file llama-3.1-1million-ctx-dark-planet-v1.01-8b-q4_k_m.gguf -c 2048 |
|
|
``` |
|
|
|
