---

license: apache-2.0

language:

• fa
• en
• zh
• ar

base_model: JibayAi/Jibay_2

library_name: transformers

pipeline_tag: text-generation

tags:

• JibayAI
• Jibay2
• OS
• jibay.ir
• multilingual
• chat
• function-calling
• text-generation
• 32k-context
• llama-cpp
• gguf-my-repo

model-index:

• name: Jibay 2

results:

- task:

type: text-generation

name: General Knowledge

dataset:

name: MMLU

type: mmlu

metrics:

- type: accuracy

value: 56.9

name: Accuracy

- task:

type: text-generation

name: Mathematical Reasoning

dataset:

name: GSM8K

type: gsm8k

metrics:

- type: accuracy

value: 70.0

name: Accuracy

- task:

type: text-generation

name: Scientific Reasoning

dataset:

name: ARC Challenge

type: ai2_arc

metrics:

- type: accuracy

value: 43.0

name: Accuracy

- task:

type: text-generation

name: Code Generation

dataset:

name: HumanEval

type: openai_humaneval

metrics:

- type: pass@1

value: 68.0

name: Pass@1

- task:

type: text-generation

name: Reading Comprehension

dataset:

name: BoolQ

type: boolq

metrics:

- type: accuracy

value: 79.0

name: Accuracy

- task:

type: text-generation

name: Commonsense Reasoning

dataset:

name: HellaSwag

type: hellaswag

metrics:

- type: accuracy

value: 61.1

name: Accuracy

- task:

type: text-generation

name: Function Calling

dataset:

name: Berkeley Function Calling Leaderboard (BFCL)

type: bfcl

metrics:

- type: overall

value: 55.0

name: Overall Score

- type: category_average

value: 51.2

name: Category Average

- task:

type: conversational

name: Persian Conversation

dataset:

name: PPRC-BENCH

type: pprc-bench

metrics:

- type: accuracy

value: 41.0

name: Accuracy

---

JibayAi/Jibay_2-Q6_K-GGUF

This model was converted to GGUF format from JibayAi/Jibay_2 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 JibayAi/Jibay_2-Q6_K-GGUF --hf-file jibay_2-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo JibayAi/Jibay_2-Q6_K-GGUF --hf-file jibay_2-q6_k.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 JibayAi/Jibay_2-Q6_K-GGUF --hf-file jibay_2-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo JibayAi/Jibay_2-Q6_K-GGUF --hf-file jibay_2-q6_k.gguf -c 2048