metadata
language:
- en
- ko
library_name: transformers
license: cc-by-nc-4.0
pipeline_tag: text-generation
model_id: kakaocorp/kanana-nano-2.1b-base
repo: kakaocorp/kanana-nano-2.1b-base
developers: Kanana LLM
training_regime: bf16 mixed precision
tags:
- TensorBlock
- GGUF
base_model: kakaocorp/kanana-nano-2.1b-base
model-index:
- name: kanana-nano-2.1b-base
results:
- task:
type: multiple_choice
name: mmlu
dataset:
name: mmlu (5-shots)
type: hails/mmlu_no_train
metrics:
- type: acc
value: 54.83
name: acc
- task:
type: generate_until
name: kmmlu
dataset:
name: kmmlu-direct (5-shots)
type: HAERAE-HUB/KMMLU
metrics:
- type: exact_match
value: 44.83
name: exact_match
- task:
type: multiple_choice
name: haerae
dataset:
name: haerae (5-shots)
type: HAERAE-HUB/HAE_RAE_BENCH
metrics:
- type: acc_norm
value: 77.09
name: acc_norm
- task:
type: generate_until
name: gsm8k
dataset:
name: gsm8k (5-shots)
type: openai/gsm8k
metrics:
- type: exact_match
value: 46.32
name: exact_match_strict
- task:
type: generate_until
name: humaneval
dataset:
name: humaneval (0-shots)
type: openai/openai_humaneval
metrics:
- type: pass@1
value: 31.1
name: pass@1
- task:
type: generate_until
name: mbpp
dataset:
name: mbpp (3-shots)
type: google-research-datasets/mbpp
metrics:
- type: pass@1
value: 46.2
name: pass@1
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
kakaocorp/kanana-nano-2.1b-base - GGUF
This repo contains GGUF format model files for kakaocorp/kanana-nano-2.1b-base.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.
Our projects
| 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 👀 |
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| kanana-nano-2.1b-base-Q2_K.gguf | Q2_K | 0.938 GB | smallest, significant quality loss - not recommended for most purposes |
| kanana-nano-2.1b-base-Q3_K_S.gguf | Q3_K_S | 1.056 GB | very small, high quality loss |
| kanana-nano-2.1b-base-Q3_K_M.gguf | Q3_K_M | 1.147 GB | very small, high quality loss |
| kanana-nano-2.1b-base-Q3_K_L.gguf | Q3_K_L | 1.203 GB | small, substantial quality loss |
| kanana-nano-2.1b-base-Q4_0.gguf | Q4_0 | 1.241 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| kanana-nano-2.1b-base-Q4_K_S.gguf | Q4_K_S | 1.304 GB | small, greater quality loss |
| kanana-nano-2.1b-base-Q4_K_M.gguf | Q4_K_M | 1.393 GB | medium, balanced quality - recommended |
| kanana-nano-2.1b-base-Q5_0.gguf | Q5_0 | 1.474 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| kanana-nano-2.1b-base-Q5_K_S.gguf | Q5_K_S | 1.502 GB | large, low quality loss - recommended |
| kanana-nano-2.1b-base-Q5_K_M.gguf | Q5_K_M | 1.579 GB | large, very low quality loss - recommended |
| kanana-nano-2.1b-base-Q6_K.gguf | Q6_K | 1.832 GB | very large, extremely low quality loss |
| kanana-nano-2.1b-base-Q8_0.gguf | Q8_0 | 2.226 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/kanana-nano-2.1b-base-GGUF --include "kanana-nano-2.1b-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/kanana-nano-2.1b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'