Instructions to use i-be-snek/mixtral_5_toy_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use i-be-snek/mixtral_5_toy_model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="i-be-snek/mixtral_5_toy_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("i-be-snek/mixtral_5_toy_model")
model = AutoModelForCausalLM.from_pretrained("i-be-snek/mixtral_5_toy_model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use i-be-snek/mixtral_5_toy_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "i-be-snek/mixtral_5_toy_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-be-snek/mixtral_5_toy_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/i-be-snek/mixtral_5_toy_model

SGLang

How to use i-be-snek/mixtral_5_toy_model with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "i-be-snek/mixtral_5_toy_model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-be-snek/mixtral_5_toy_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "i-be-snek/mixtral_5_toy_model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-be-snek/mixtral_5_toy_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use i-be-snek/mixtral_5_toy_model with Docker Model Runner:
```
docker model run hf.co/i-be-snek/mixtral_5_toy_model
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

mixtral_5_toy_model

This model is a fine-tuned version of on the arrow dataset. It achieves the following results on the evaluation set:

Loss: 8.6838

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: 0.0001
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 256
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 780
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	10.9749
10.7986	1.256	50	10.5715
10.3611	2.512	100	10.1266
9.8898	3.768	150	9.7008
9.5128	5.0	200	9.4023
9.169	6.256	250	9.0760
8.833	7.5120	300	8.8510
8.5735	8.768	350	8.6894
8.3489	10.0	400	8.6102
8.134	11.256	450	8.5842
7.9193	12.512	500	8.5650
7.6925	13.768	550	8.5667
7.4401	15.0	600	8.5921
7.1474	16.256	650	8.6214
6.9251	17.512	700	8.6492
6.7407	18.768	750	8.6718

Framework versions

Transformers 4.53.1
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 3

Safetensors

Model size

0.2B params

Tensor type

F32