metadata
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- language
- granite-3.0
- llama-cpp
- gguf-my-repo
base_model: ibm-granite/granite-3.0-2b-instruct
model-index:
- name: granite-3.0-2b-instruct
results:
- task:
type: text-generation
dataset:
name: IFEval
type: instruction-following
metrics:
- type: pass@1
value: 46.07
name: pass@1
- type: pass@1
value: 7.66
name: pass@1
- task:
type: text-generation
dataset:
name: AGI-Eval
type: human-exams
metrics:
- type: pass@1
value: 29.75
name: pass@1
- type: pass@1
value: 56.03
name: pass@1
- type: pass@1
value: 27.92
name: pass@1
- task:
type: text-generation
dataset:
name: OBQA
type: commonsense
metrics:
- type: pass@1
value: 43.2
name: pass@1
- type: pass@1
value: 66.36
name: pass@1
- type: pass@1
value: 76.79
name: pass@1
- type: pass@1
value: 71.9
name: pass@1
- type: pass@1
value: 53.37
name: pass@1
- task:
type: text-generation
dataset:
name: BoolQ
type: reading-comprehension
metrics:
- type: pass@1
value: 84.89
name: pass@1
- type: pass@1
value: 19.73
name: pass@1
- task:
type: text-generation
dataset:
name: ARC-C
type: reasoning
metrics:
- type: pass@1
value: 54.35
name: pass@1
- type: pass@1
value: 28.61
name: pass@1
- type: pass@1
value: 43.74
name: pass@1
- task:
type: text-generation
dataset:
name: HumanEvalSynthesis
type: code
metrics:
- type: pass@1
value: 50.61
name: pass@1
- type: pass@1
value: 45.58
name: pass@1
- type: pass@1
value: 51.83
name: pass@1
- type: pass@1
value: 41
name: pass@1
- task:
type: text-generation
dataset:
name: GSM8K
type: math
metrics:
- type: pass@1
value: 59.66
name: pass@1
- type: pass@1
value: 23.66
name: pass@1
- task:
type: text-generation
dataset:
name: PAWS-X (7 langs)
type: multilingual
metrics:
- type: pass@1
value: 61.42
name: pass@1
- type: pass@1
value: 37.13
name: pass@1
davelsphere/granite-3.0-2b-instruct-Q4_K_M-GGUF
This model was converted to GGUF format from ibm-granite/granite-3.0-2b-instruct 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 davelsphere/granite-3.0-2b-instruct-Q4_K_M-GGUF --hf-file granite-3.0-2b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo davelsphere/granite-3.0-2b-instruct-Q4_K_M-GGUF --hf-file granite-3.0-2b-instruct-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 davelsphere/granite-3.0-2b-instruct-Q4_K_M-GGUF --hf-file granite-3.0-2b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo davelsphere/granite-3.0-2b-instruct-Q4_K_M-GGUF --hf-file granite-3.0-2b-instruct-q4_k_m.gguf -c 2048