Instructions to use RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/VirgiF_-_continue_pretrain_gemma_more_pause-gguf:Q4_K_M

Run and chat with the model

lemonade run user.VirgiF_-_continue_pretrain_gemma_more_pause-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

continue_pretrain_gemma_more_pause - GGUF

Model creator: https://huggingface.co/VirgiF/
Original model: https://huggingface.co/VirgiF/continue_pretrain_gemma_more_pause/

Name	Quant method	Size
continue_pretrain_gemma_more_pause.Q2_K.gguf	Q2_K	1.08GB
continue_pretrain_gemma_more_pause.IQ3_XS.gguf	IQ3_XS	1.16GB
continue_pretrain_gemma_more_pause.IQ3_S.gguf	IQ3_S	1.2GB
continue_pretrain_gemma_more_pause.Q3_K_S.gguf	Q3_K_S	1.2GB
continue_pretrain_gemma_more_pause.IQ3_M.gguf	IQ3_M	1.22GB
continue_pretrain_gemma_more_pause.Q3_K.gguf	Q3_K	1.29GB
continue_pretrain_gemma_more_pause.Q3_K_M.gguf	Q3_K_M	1.29GB
continue_pretrain_gemma_more_pause.Q3_K_L.gguf	Q3_K_L	1.36GB
continue_pretrain_gemma_more_pause.IQ4_XS.gguf	IQ4_XS	1.4GB
continue_pretrain_gemma_more_pause.Q4_0.gguf	Q4_0	1.44GB
continue_pretrain_gemma_more_pause.IQ4_NL.gguf	IQ4_NL	1.45GB
continue_pretrain_gemma_more_pause.Q4_K_S.gguf	Q4_K_S	1.45GB
continue_pretrain_gemma_more_pause.Q4_K.gguf	Q4_K	1.52GB
continue_pretrain_gemma_more_pause.Q4_K_M.gguf	Q4_K_M	1.52GB
continue_pretrain_gemma_more_pause.Q4_1.gguf	Q4_1	1.56GB
continue_pretrain_gemma_more_pause.Q5_0.gguf	Q5_0	1.68GB
continue_pretrain_gemma_more_pause.Q5_K_S.gguf	Q5_K_S	1.68GB
continue_pretrain_gemma_more_pause.Q5_K.gguf	Q5_K	1.71GB
continue_pretrain_gemma_more_pause.Q5_K_M.gguf	Q5_K_M	1.71GB
continue_pretrain_gemma_more_pause.Q5_1.gguf	Q5_1	1.79GB
continue_pretrain_gemma_more_pause.Q6_K.gguf	Q6_K	1.92GB
continue_pretrain_gemma_more_pause.Q8_0.gguf	Q8_0	2.49GB

Original model description:

library_name: transformers license: gemma base_model: google/gemma-2b tags: - trl - sft - generated_from_trainer model-index: - name: continue_pretrain_gemma_more_pause results: []

continue_pretrain_gemma_more_pause

This model is a fine-tuned version of google/gemma-2b on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.1.2+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 347

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support