---

license: apache-2.0

tags:

• mergekit
• merge
• moe
• llama-cpp
• gguf-my-repo

base_model: osanseviero/mistral-instruct-moe-experimental

model-index:

• name: mistral-instruct-moe-experimental

results:

- task:

type: text-generation

name: Text Generation

dataset:

name: AI2 Reasoning Challenge (25-Shot)

type: ai2_arc

config: ARC-Challenge

split: test

args:

num_few_shot: 25

metrics:

- type: acc_norm

value: 61.01

name: normalized accuracy

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

- task:

type: text-generation

name: Text Generation

dataset:

name: HellaSwag (10-Shot)

type: hellaswag

split: validation

args:

num_few_shot: 10

metrics:

- type: acc_norm

value: 81.55

name: normalized accuracy

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

- task:

type: text-generation

name: Text Generation

dataset:

name: MMLU (5-Shot)

type: cais/mmlu

config: all

split: test

args:

num_few_shot: 5

metrics:

- type: acc

value: 58.22

name: accuracy

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

- task:

type: text-generation

name: Text Generation

dataset:

name: TruthfulQA (0-shot)

type: truthful_qa

config: multiple_choice

split: validation

args:

num_few_shot: 0

metrics:

- type: mc2

value: 60.4

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

- task:

type: text-generation

name: Text Generation

dataset:

name: Winogrande (5-shot)

type: winogrande

config: winogrande_xl

split: validation

args:

num_few_shot: 5

metrics:

- type: acc

value: 76.09

name: accuracy

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

- task:

type: text-generation

name: Text Generation

dataset:

name: GSM8k (5-shot)

type: gsm8k

config: main

split: test

args:

num_few_shot: 5

metrics:

- type: acc

value: 31.08

name: accuracy

source:

url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental

name: Open LLM Leaderboard

---

NonMiFrega/mistral-instruct-moe-experimental-Q4_K_M-GGUF

This model was converted to GGUF format from osanseviero/mistral-instruct-moe-experimental using llama.cpp via the ggml.ai's GGUF-my-repo space.

Refer to the original model card for more details on the model.

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 NonMiFrega/mistral-instruct-moe-experimental-Q4_K_M-GGUF --hf-file mistral-instruct-moe-experimental-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NonMiFrega/mistral-instruct-moe-experimental-Q4_K_M-GGUF --hf-file mistral-instruct-moe-experimental-q4_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 NonMiFrega/mistral-instruct-moe-experimental-Q4_K_M-GGUF --hf-file mistral-instruct-moe-experimental-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo NonMiFrega/mistral-instruct-moe-experimental-Q4_K_M-GGUF --hf-file mistral-instruct-moe-experimental-q4_k_m.gguf -c 2048