metadata
pipeline_tag: text-generation
inference: true
license: apache-2.0
datasets:
- codeparrot/github-code-clean
- bigcode/starcoderdata
- open-web-math/open-web-math
- math-ai/StackMathQA
metrics:
- code_eval
library_name: transformers
tags:
- code
- granite
- TensorBlock
- GGUF
base_model: ibm-granite/granite-20b-code-base-r1.1
model-index:
- name: granite-20b-code-base-r1.1
results:
- task:
type: text-generation
dataset:
name: HumanEvalSynthesis(Python)
type: bigcode/humanevalpack
metrics:
- type: pass@1
value: 48.2
name: pass@1
- type: pass@1
value: 56.1
name: pass@1
- type: pass@1
value: 59.8
name: pass@1
- type: pass@1
value: 33.5
name: pass@1
- type: pass@1
value: 50.6
name: pass@1
- type: pass@1
value: 40.9
name: pass@1
- type: pass@1
value: 28.7
name: pass@1
- type: pass@1
value: 24.4
name: pass@1
- type: pass@1
value: 43.3
name: pass@1
- type: pass@1
value: 13.8
name: pass@1
- type: pass@1
value: 29.9
name: pass@1
- type: pass@1
value: 18.3
name: pass@1
- type: pass@1
value: 22
name: pass@1
- type: pass@1
value: 24.4
name: pass@1
- type: pass@1
value: 32.3
name: pass@1
- type: pass@1
value: 28
name: pass@1
- type: pass@1
value: 30.5
name: pass@1
- type: pass@1
value: 13.4
name: pass@1
ibm-granite/granite-20b-code-base-r1.1 - GGUF
This repo contains GGUF format model files for ibm-granite/granite-20b-code-base-r1.1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Forge | |
|---|---|
|
|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| Awesome MCP Servers | TensorBlock Studio |
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| granite-20b-code-base-r1.1-Q2_K.gguf | Q2_K | 7.929 GB | smallest, significant quality loss - not recommended for most purposes |
| granite-20b-code-base-r1.1-Q3_K_S.gguf | Q3_K_S | 8.935 GB | very small, high quality loss |
| granite-20b-code-base-r1.1-Q3_K_M.gguf | Q3_K_M | 10.566 GB | very small, high quality loss |
| granite-20b-code-base-r1.1-Q3_K_L.gguf | Q3_K_L | 11.737 GB | small, substantial quality loss |
| granite-20b-code-base-r1.1-Q4_0.gguf | Q4_0 | 11.552 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| granite-20b-code-base-r1.1-Q4_K_S.gguf | Q4_K_S | 11.666 GB | small, greater quality loss |
| granite-20b-code-base-r1.1-Q4_K_M.gguf | Q4_K_M | 12.820 GB | medium, balanced quality - recommended |
| granite-20b-code-base-r1.1-Q5_0.gguf | Q5_0 | 14.016 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| granite-20b-code-base-r1.1-Q5_K_S.gguf | Q5_K_S | 14.016 GB | large, low quality loss - recommended |
| granite-20b-code-base-r1.1-Q5_K_M.gguf | Q5_K_M | 14.809 GB | large, very low quality loss - recommended |
| granite-20b-code-base-r1.1-Q6_K.gguf | Q6_K | 16.634 GB | very large, extremely low quality loss |
| granite-20b-code-base-r1.1-Q8_0.gguf | Q8_0 | 21.481 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-20b-code-base-r1.1-GGUF --include "granite-20b-code-base-r1.1-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-20b-code-base-r1.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'