Hugging Face's logo

Triangle104
/
L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF

Transformers
GGUF
Not-For-All-Audiences
mergekit
llama-cpp
gguf-my-repo
Inference Endpoints
conversational
Model card Files Community
L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF / README.md
Triangle104's picture
Triangle104
Update README.md
2682afe verified
preview code
|
raw
history blame contribute delete
2.98 kB
metadata
license: llama3
license_name: llama3
license_link: LICENSE
library_name: transformers
tags:
  - not-for-all-audiences
  - mergekit
  - llama-cpp
  - gguf-my-repo
base_model: crestf411/L3.1-8B-Dark-Planet-Slush

Triangle104/L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF

This model was converted to GGUF format from crestf411/L3.1-8B-Dark-Planet-Slush using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Model details:

This is based on v1.1 and includes a merge with DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B.

Parameter suggestions:

I did all my testing with temp 1, min-p 0.1, DRY 0.8. I enabled XTC at higher contexts.

Merge Details

This model was merged using the TIES merge method using meta-llama/Llama-3.1-8B as a base.

Configuration

The following YAML configuration was used to produce this model:

models:

  • model: stage1-on-instruct parameters: weight: 1 density: 1
  • model: stage2-on-stage1 parameters: weight: 1 density: 1
  • model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B parameters: weight: 1 density: 1
  • model: meta-llama/Llama-3.1-8B-Instruct parameters: weight: 1.3 density: 1 merge_method: ties base_model: meta-llama/Llama-3.1-8B parameters: weight: 1 density: 1 normalize: true int8_mask: true tokenizer_source: meta-llama/Llama-3.1-8B-Instruct dtype: bfloat16

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI: 

llama-cli --hf-repo Triangle104/L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF --hf-file l3.1-8b-dark-planet-slush-q5_k_m.gguf -p "The meaning to life and the universe is"

Server: 

llama-server --hf-repo Triangle104/L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF --hf-file l3.1-8b-dark-planet-slush-q5_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps 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/L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF --hf-file l3.1-8b-dark-planet-slush-q5_k_m.gguf -p "The meaning to life and the universe is"

or 

./llama-server --hf-repo Triangle104/L3.1-8B-Dark-Planet-Slush-Q5_K_M-GGUF --hf-file l3.1-8b-dark-planet-slush-q5_k_m.gguf -c 2048