metadata
license: openrail
datasets:
- Locutusque/ColumnedChatCombined
language:
- en
metrics:
- bleu
- perplexity
- loss
- reward
- penalty
widget:
- text: '<|USER|> Hello! <|ASSISTANT|> '
pipeline_tag: conversational
inference:
parameters:
temperature: 0.5
do_sample: true
top_p: 0.5
top_k: 30
max_new_tokens: 250
repetition_penalty: 1.15
base_model: Locutusque/gpt2-conversational-or-qa
tags:
- TensorBlock
- GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Locutusque/gpt2-conversational-or-qa - GGUF
This repo contains GGUF format model files for Locutusque/gpt2-conversational-or-qa.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
gpt2-conversational-or-qa-Q2_K.gguf | Q2_K | 0.076 GB | smallest, significant quality loss - not recommended for most purposes |
gpt2-conversational-or-qa-Q3_K_S.gguf | Q3_K_S | 0.084 GB | very small, high quality loss |
gpt2-conversational-or-qa-Q3_K_M.gguf | Q3_K_M | 0.091 GB | very small, high quality loss |
gpt2-conversational-or-qa-Q3_K_L.gguf | Q3_K_L | 0.095 GB | small, substantial quality loss |
gpt2-conversational-or-qa-Q4_0.gguf | Q4_0 | 0.099 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
gpt2-conversational-or-qa-Q4_K_S.gguf | Q4_K_S | 0.100 GB | small, greater quality loss |
gpt2-conversational-or-qa-Q4_K_M.gguf | Q4_K_M | 0.105 GB | medium, balanced quality - recommended |
gpt2-conversational-or-qa-Q5_0.gguf | Q5_0 | 0.114 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
gpt2-conversational-or-qa-Q5_K_S.gguf | Q5_K_S | 0.114 GB | large, low quality loss - recommended |
gpt2-conversational-or-qa-Q5_K_M.gguf | Q5_K_M | 0.118 GB | large, very low quality loss - recommended |
gpt2-conversational-or-qa-Q6_K.gguf | Q6_K | 0.129 GB | very large, extremely low quality loss |
gpt2-conversational-or-qa-Q8_0.gguf | Q8_0 | 0.165 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/gpt2-conversational-or-qa-GGUF --include "gpt2-conversational-or-qa-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/gpt2-conversational-or-qa-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'