library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
base_model: bunnycore/Phi-3.5-mini-TitanFusion-0.1
model-index:
- name: Phi-3.5-mini-TitanFusion-0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 52.28
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 35.45
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 6.19
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 10.85
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 15.8
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 31.18
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-3.5-mini-TitanFusion-0.1
name: Open LLM Leaderboard
Triangle104/Phi-3.5-mini-TitanFusion-0.1-Q5_K_S-GGUF
This model was converted to GGUF format from bunnycore/Phi-3.5-mini-TitanFusion-0.1 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 a merged pre-trained language model created using the TIES merge method. It is based on the microsoft/Phi-3.5-mini-instruct model and incorporates the knowledge and capabilities of the nbeerbower/phi3.5-gutenberg-4B and ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 models.
Capabilities: Roleplay: The model can engage in role-playing scenarios, taking on different personas and responding to prompts in a character-appropriate manner. Creative Writing: It can assist in creative writing tasks, such as brainstorming ideas, generating plotlines, or developing characters. Reasoning: The model can reason about information and draw conclusions based on the data it has been trained on. This is a merge of pre-trained language models created using mergekit.
Merge Details Merge Method This model was merged using the TIES merge method using microsoft/Phi-3.5-mini-instruct as a base.
Models Merged The following models were included in the merge:
nbeerbower/phi3.5-gutenberg-4B ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 Configuration The following YAML configuration was used to produce this model:
models:
- model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 parameters: weight: 1
- model: nbeerbower/phi3.5-gutenberg-4B parameters: weight: 1
merge_method: ties base_model: microsoft/Phi-3.5-mini-instruct parameters: density: 1 normalize: true int8_mask: true 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/Phi-3.5-mini-TitanFusion-0.1-Q5_K_S-GGUF --hf-file phi-3.5-mini-titanfusion-0.1-q5_k_s.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Triangle104/Phi-3.5-mini-TitanFusion-0.1-Q5_K_S-GGUF --hf-file phi-3.5-mini-titanfusion-0.1-q5_k_s.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/Phi-3.5-mini-TitanFusion-0.1-Q5_K_S-GGUF --hf-file phi-3.5-mini-titanfusion-0.1-q5_k_s.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Triangle104/Phi-3.5-mini-TitanFusion-0.1-Q5_K_S-GGUF --hf-file phi-3.5-mini-titanfusion-0.1-q5_k_s.gguf -c 2048