metadata
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- language
- granite-3.0
- TensorBlock
- GGUF
base_model: ibm-granite/granite-3.0-8b-base
model-index:
- name: granite-3.0-8b-base
results:
- task:
type: text-generation
dataset:
name: MMLU
type: human-exams
metrics:
- type: pass@1
value: 65.54
name: pass@1
- type: pass@1
value: 33.27
name: pass@1
- type: pass@1
value: 34.45
name: pass@1
- task:
type: text-generation
dataset:
name: WinoGrande
type: commonsense
metrics:
- type: pass@1
value: 80.9
name: pass@1
- type: pass@1
value: 46.8
name: pass@1
- type: pass@1
value: 67.8
name: pass@1
- type: pass@1
value: 82.32
name: pass@1
- type: pass@1
value: 83.61
name: pass@1
- type: pass@1
value: 52.89
name: pass@1
- task:
type: text-generation
dataset:
name: BoolQ
type: reading-comprehension
metrics:
- type: pass@1
value: 86.97
name: pass@1
- type: pass@1
value: 32.92
name: pass@1
- task:
type: text-generation
dataset:
name: ARC-C
type: reasoning
metrics:
- type: pass@1
value: 63.4
name: pass@1
- type: pass@1
value: 32.13
name: pass@1
- type: pass@1
value: 49.31
name: pass@1
- type: pass@1
value: 41.08
name: pass@1
- task:
type: text-generation
dataset:
name: HumanEval
type: code
metrics:
- type: pass@1
value: 52.44
name: pass@1
- type: pass@1
value: 41.4
name: pass@1
- task:
type: text-generation
dataset:
name: GSM8K
type: math
metrics:
- type: pass@1
value: 64.06
name: pass@1
- type: pass@1
value: 29.28
name: pass@1
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
ibm-granite/granite-3.0-8b-base - GGUF
This repo contains GGUF format model files for ibm-granite/granite-3.0-8b-base.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| granite-3.0-8b-base-Q2_K.gguf | Q2_K | 3.104 GB | smallest, significant quality loss - not recommended for most purposes |
| granite-3.0-8b-base-Q3_K_S.gguf | Q3_K_S | 3.592 GB | very small, high quality loss |
| granite-3.0-8b-base-Q3_K_M.gguf | Q3_K_M | 3.997 GB | very small, high quality loss |
| granite-3.0-8b-base-Q3_K_L.gguf | Q3_K_L | 4.349 GB | small, substantial quality loss |
| granite-3.0-8b-base-Q4_0.gguf | Q4_0 | 4.651 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| granite-3.0-8b-base-Q4_K_S.gguf | Q4_K_S | 4.686 GB | small, greater quality loss |
| granite-3.0-8b-base-Q4_K_M.gguf | Q4_K_M | 4.943 GB | medium, balanced quality - recommended |
| granite-3.0-8b-base-Q5_0.gguf | Q5_0 | 5.647 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| granite-3.0-8b-base-Q5_K_S.gguf | Q5_K_S | 5.647 GB | large, low quality loss - recommended |
| granite-3.0-8b-base-Q5_K_M.gguf | Q5_K_M | 5.797 GB | large, very low quality loss - recommended |
| granite-3.0-8b-base-Q6_K.gguf | Q6_K | 6.705 GB | very large, extremely low quality loss |
| granite-3.0-8b-base-Q8_0.gguf | Q8_0 | 8.684 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/granite-3.0-8b-base-GGUF --include "granite-3.0-8b-base-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/granite-3.0-8b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'