Instructions to use RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-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/interview-eval_-_zephyr-7b-math-case-8-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/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-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/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-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/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-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/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/interview-eval_-_zephyr-7b-math-case-8-gguf:Q4_K_M

Run and chat with the model

lemonade run user.interview-eval_-_zephyr-7b-math-case-8-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

zephyr-7b-math-case-8 - GGUF

Model creator: https://huggingface.co/interview-eval/
Original model: https://huggingface.co/interview-eval/zephyr-7b-math-case-8/

Name	Quant method	Size
zephyr-7b-math-case-8.Q2_K.gguf	Q2_K	2.53GB
zephyr-7b-math-case-8.IQ3_XS.gguf	IQ3_XS	2.81GB
zephyr-7b-math-case-8.IQ3_S.gguf	IQ3_S	2.96GB
zephyr-7b-math-case-8.Q3_K_S.gguf	Q3_K_S	2.95GB
zephyr-7b-math-case-8.IQ3_M.gguf	IQ3_M	3.06GB
zephyr-7b-math-case-8.Q3_K.gguf	Q3_K	3.28GB
zephyr-7b-math-case-8.Q3_K_M.gguf	Q3_K_M	3.28GB
zephyr-7b-math-case-8.Q3_K_L.gguf	Q3_K_L	3.56GB
zephyr-7b-math-case-8.IQ4_XS.gguf	IQ4_XS	3.67GB
zephyr-7b-math-case-8.Q4_0.gguf	Q4_0	3.83GB
zephyr-7b-math-case-8.IQ4_NL.gguf	IQ4_NL	3.87GB
zephyr-7b-math-case-8.Q4_K_S.gguf	Q4_K_S	3.86GB
zephyr-7b-math-case-8.Q4_K.gguf	Q4_K	4.07GB
zephyr-7b-math-case-8.Q4_K_M.gguf	Q4_K_M	4.07GB
zephyr-7b-math-case-8.Q4_1.gguf	Q4_1	4.24GB
zephyr-7b-math-case-8.Q5_0.gguf	Q5_0	4.65GB
zephyr-7b-math-case-8.Q5_K_S.gguf	Q5_K_S	4.65GB
zephyr-7b-math-case-8.Q5_K.gguf	Q5_K	4.78GB
zephyr-7b-math-case-8.Q5_K_M.gguf	Q5_K_M	4.78GB
zephyr-7b-math-case-8.Q5_1.gguf	Q5_1	5.07GB
zephyr-7b-math-case-8.Q6_K.gguf	Q6_K	5.53GB
zephyr-7b-math-case-8.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: alignment-handbook/zephyr-7b-sft-full tags: - alignment-handbook - trl - sft - generated_from_trainer - trl - sft - generated_from_trainer datasets: - EunsuKim/GSM8K model-index: - name: zephyr-7b-math-case-8 results: []

zephyr-7b-math-case-8

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/GSM8K dataset. It achieves the following results on the evaluation set:

Loss: 0.0276

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.0201	1.0	4	0.8704
0.9676	2.0	8	0.6483
0.7053	3.0	12	0.4601
0.4784	4.0	16	0.2716
0.2487	5.0	20	0.1375
0.2487	6.0	24	0.0688
0.1048	7.0	28	0.0426
0.0523	8.0	32	0.0332
0.0354	9.0	36	0.0287
0.0285	10.0	40	0.0276

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

Downloads last month: 296

GGUF

Model size

7B params

Architecture

llama

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