metadata
tags:
- generated_from_trainer
- TensorBlock
- GGUF
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
repetition_penalty: 1.1
no_repeat_ngram_size: 5
guidance_scale: 1.01
eta_cutoff: 0.001
widget:
- text: My name is El Microondas the Wise and
example_title: El Microondas
- text: A meme is
example_title: meme
- text: >-
Barack Obama nominated Hilary Clinton as his secretary of state on Monday.
He chose her because she had
example_title: Coreference resolution
- text: >-
On a shelf, there are five books: a gray book, a red book, a purple book,
a blue book, and a black book
example_title: Logic puzzles
- text: >-
The two men running to become New York City's next mayor will face off in
their first debate Wednesday night
example_title: Reading comprehension
pipeline_tag: text-generation
license: apache-2.0
datasets:
- euirim/goodwiki
language:
- en
base_model: pszemraj/pythia-31m-goodwiki-deduped-2048-scratch
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
pszemraj/pythia-31m-goodwiki-deduped-2048-scratch - GGUF
This repo contains GGUF format model files for pszemraj/pythia-31m-goodwiki-deduped-2048-scratch.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
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 👀 |
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| pythia-31m-goodwiki-deduped-2048-scratch-Q2_K.gguf | Q2_K | 0.017 GB | smallest, significant quality loss - not recommended for most purposes |
| pythia-31m-goodwiki-deduped-2048-scratch-Q3_K_S.gguf | Q3_K_S | 0.019 GB | very small, high quality loss |
| pythia-31m-goodwiki-deduped-2048-scratch-Q3_K_M.gguf | Q3_K_M | 0.019 GB | very small, high quality loss |
| pythia-31m-goodwiki-deduped-2048-scratch-Q3_K_L.gguf | Q3_K_L | 0.019 GB | small, substantial quality loss |
| pythia-31m-goodwiki-deduped-2048-scratch-Q4_0.gguf | Q4_0 | 0.021 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| pythia-31m-goodwiki-deduped-2048-scratch-Q4_K_S.gguf | Q4_K_S | 0.021 GB | small, greater quality loss |
| pythia-31m-goodwiki-deduped-2048-scratch-Q4_K_M.gguf | Q4_K_M | 0.021 GB | medium, balanced quality - recommended |
| pythia-31m-goodwiki-deduped-2048-scratch-Q5_0.gguf | Q5_0 | 0.023 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| pythia-31m-goodwiki-deduped-2048-scratch-Q5_K_S.gguf | Q5_K_S | 0.023 GB | large, low quality loss - recommended |
| pythia-31m-goodwiki-deduped-2048-scratch-Q5_K_M.gguf | Q5_K_M | 0.023 GB | large, very low quality loss - recommended |
| pythia-31m-goodwiki-deduped-2048-scratch-Q6_K.gguf | Q6_K | 0.025 GB | very large, extremely low quality loss |
| pythia-31m-goodwiki-deduped-2048-scratch-Q8_0.gguf | Q8_0 | 0.032 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/pythia-31m-goodwiki-deduped-2048-scratch-GGUF --include "pythia-31m-goodwiki-deduped-2048-scratch-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/pythia-31m-goodwiki-deduped-2048-scratch-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'