|
--- |
|
language: |
|
- sv |
|
- en |
|
- 'no' |
|
- da |
|
license: mit |
|
tags: |
|
- pretrained |
|
- flashback |
|
- web |
|
- conversational |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
pipeline_tag: text-generation |
|
widget: |
|
- text: Jag tycker att det är roligt med |
|
--- |
|
# 🦙 Llama-3-8B-flashback-v1-Q5_K_M-GGUF |
|
|
|
 |
|
|
|
Llama-3-8B-flashback-v1 is a continuation of the pretraining process for the base meta-llama/Meta-Llama-3-8B model, utilizing 2 251 233 forum threads from the Swedish website https://www.flashback.org/. Which is rougly 40GB of text. |
|
It is a full finetune for three epochs. |
|
|
|
# catbash/Llama-3-8B-flashback-v1-Q5_K_M-GGUF |
|
This model was converted to GGUF format from [`timpal0l/Llama-3-8B-flashback-v1`](https://huggingface.co/timpal0l/Llama-3-8B-flashback-v1) 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/timpal0l/Llama-3-8B-flashback-v1) 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 catbash/Llama-3-8B-flashback-v1-Q5_K_M-GGUF --hf-file llama-3-8b-flashback-v1-q5_k_m-imat.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo catbash/Llama-3-8B-flashback-v1-Q5_K_M-GGUF --hf-file llama-3-8b-flashback-v1-q5_k_m-imat.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 catbash/Llama-3-8B-flashback-v1-Q5_K_M-GGUF --hf-file llama-3-8b-flashback-v1-q5_k_m-imat.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo catbash/Llama-3-8B-flashback-v1-Q5_K_M-GGUF --hf-file llama-3-8b-flashback-v1-q5_k_m-imat.gguf -c 2048 |
|
``` |
|
|
