Hugging Face's logo

tensorblock
/
dolphincoder-starcoder2-15b-GGUF

GGUF
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
dolphincoder-starcoder2-15b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
a5cd3cb verified
preview code
|
raw
history blame contribute delete
5.53 kB
metadata
datasets:
  - cognitivecomputations/dolphin
  - jondurbin/airoboros-2.2.1
  - cognitivecomputations/dolphin-coder
  - teknium/openhermes
  - ise-uiuc/Magicoder-OSS-Instruct-75K
  - ise-uiuc/Magicoder-Evol-Instruct-110K
  - m-a-p/Code-Feedback
  - m-a-p/CodeFeedback-Filtered-Instruction
language:
  - en
license: bigcode-openrail-m
base_model: cognitivecomputations/dolphincoder-starcoder2-15b
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

cognitivecomputations/dolphincoder-starcoder2-15b - GGUF

This repo contains GGUF format model files for cognitivecomputations/dolphincoder-starcoder2-15b.

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

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
dolphincoder-starcoder2-15b-Q2_K.gguf Q2_K 6.193 GB smallest, significant quality loss - not recommended for most purposes
dolphincoder-starcoder2-15b-Q3_K_S.gguf Q3_K_S 6.986 GB very small, high quality loss
dolphincoder-starcoder2-15b-Q3_K_M.gguf Q3_K_M 8.044 GB very small, high quality loss
dolphincoder-starcoder2-15b-Q3_K_L.gguf Q3_K_L 8.965 GB small, substantial quality loss
dolphincoder-starcoder2-15b-Q4_0.gguf Q4_0 9.065 GB legacy; small, very high quality loss - prefer using Q3_K_M
dolphincoder-starcoder2-15b-Q4_K_S.gguf Q4_K_S 9.161 GB small, greater quality loss
dolphincoder-starcoder2-15b-Q4_K_M.gguf Q4_K_M 9.860 GB medium, balanced quality - recommended
dolphincoder-starcoder2-15b-Q5_0.gguf Q5_0 11.022 GB legacy; medium, balanced quality - prefer using Q4_K_M
dolphincoder-starcoder2-15b-Q5_K_S.gguf Q5_K_S 11.022 GB large, low quality loss - recommended
dolphincoder-starcoder2-15b-Q5_K_M.gguf Q5_K_M 11.432 GB large, very low quality loss - recommended
dolphincoder-starcoder2-15b-Q6_K.gguf Q6_K 13.101 GB very large, extremely low quality loss
dolphincoder-starcoder2-15b-Q8_0.gguf Q8_0 16.965 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/dolphincoder-starcoder2-15b-GGUF --include "dolphincoder-starcoder2-15b-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/dolphincoder-starcoder2-15b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'