Hugging Face's logo

tensorblock
/
mistral-1L-tiny-GGUF

GGUF
Generated from Trainer
TensorBlock
GGUF
Eval Results
Inference Endpoints
Model card Files Community
mistral-1L-tiny-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
028cdce verified
preview code
|
raw
history blame contribute delete
4.9 kB
metadata
tags:
  - generated_from_trainer
  - TensorBlock
  - GGUF
datasets:
  - roneneldan/TinyStories
metrics:
  - accuracy
base_model: nilq/mistral-1L-tiny
model-index:
  - name: mistral-1L-tiny
    results:
      - task:
          type: text-generation
          name: Causal Language Modeling
        dataset:
          name: roneneldan/TinyStories
          type: roneneldan/TinyStories
        metrics:
          - type: accuracy
            value: 0.5792084706530948
            name: Accuracy
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

nilq/mistral-1L-tiny - GGUF

This repo contains GGUF format model files for nilq/mistral-1L-tiny.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template

Model file specification

Filename Quant type File Size Description
mistral-1L-tiny-Q2_K.gguf Q2_K 0.020 GB smallest, significant quality loss - not recommended for most purposes
mistral-1L-tiny-Q3_K_S.gguf Q3_K_S 0.022 GB very small, high quality loss
mistral-1L-tiny-Q3_K_M.gguf Q3_K_M 0.022 GB very small, high quality loss
mistral-1L-tiny-Q3_K_L.gguf Q3_K_L 0.022 GB small, substantial quality loss
mistral-1L-tiny-Q4_0.gguf Q4_0 0.025 GB legacy; small, very high quality loss - prefer using Q3_K_M
mistral-1L-tiny-Q4_K_S.gguf Q4_K_S 0.025 GB small, greater quality loss
mistral-1L-tiny-Q4_K_M.gguf Q4_K_M 0.025 GB medium, balanced quality - recommended
mistral-1L-tiny-Q5_0.gguf Q5_0 0.027 GB legacy; medium, balanced quality - prefer using Q4_K_M
mistral-1L-tiny-Q5_K_S.gguf Q5_K_S 0.027 GB large, low quality loss - recommended
mistral-1L-tiny-Q5_K_M.gguf Q5_K_M 0.027 GB large, very low quality loss - recommended
mistral-1L-tiny-Q6_K.gguf Q6_K 0.030 GB very large, extremely low quality loss
mistral-1L-tiny-Q8_0.gguf Q8_0 0.038 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/mistral-1L-tiny-GGUF --include "mistral-1L-tiny-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/mistral-1L-tiny-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'