Instructions to use Locutusque/TinyMistral-248M-v2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/TinyMistral-248M-v2.5 with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/TinyMistral-248M-v2.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/TinyMistral-248M-v2.5")
model = AutoModelForMultimodalLM.from_pretrained("Locutusque/TinyMistral-248M-v2.5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Locutusque/TinyMistral-248M-v2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/TinyMistral-248M-v2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/TinyMistral-248M-v2.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/TinyMistral-248M-v2.5

SGLang

How to use Locutusque/TinyMistral-248M-v2.5 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 "Locutusque/TinyMistral-248M-v2.5" \
    --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": "Locutusque/TinyMistral-248M-v2.5",
		"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 "Locutusque/TinyMistral-248M-v2.5" \
        --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": "Locutusque/TinyMistral-248M-v2.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/TinyMistral-248M-v2.5 with Docker Model Runner:
```
docker model run hf.co/Locutusque/TinyMistral-248M-v2.5
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TinyMistral-248M-v2.5

This model was created by merging TinyMistral-248M-v1 and v2, then further pretraining on synthetic textbooks. The resulting model's performance is superior to both, after personal evaluation.

During training, this model reached an average perplexity score of 4, outperforming V1 by nearly 7x, and V2 by 4x.

You can use the following config to reproduce the merged model:

base_model: Locutusque/TinyMistral-248M-v2
dtype: float16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 12]
    model: Locutusque/TinyMistral-248M
    parameters:
      density: [1.0, 0.7, 0.1]
      weight: 1.0
  - layer_range: [0, 12]
    model: Locutusque/TinyMistral-248M-v2
    parameters:
      density: 0.5
      weight: [0.0, 0.3, 0.7, 1.0]

This model can also answer basic questions, without needing to do any fine-tuning.

This model was also created as an attempt to fix the issue with V2 - the weights were prone to exploding gradients, making it difficult to fine-tune. This model is easier to fine-tune.

To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.29
AI2 Reasoning Challenge (25-Shot)	24.57
HellaSwag (10-Shot)	27.49
MMLU (5-Shot)	23.15
TruthfulQA (0-shot)	46.72
Winogrande (5-shot)	47.83
GSM8k (5-shot)	0.00

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	3.87
IFEval (0-Shot)	13.36
BBH (3-Shot)	3.18
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	0.11
MuSR (0-shot)	5.07
MMLU-PRO (5-shot)	1.50

Downloads last month: 244

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for Locutusque/TinyMistral-248M-v2.5

Finetunes

3 models

Merges

1 model

Quantizations

6 models

Datasets used to train Locutusque/TinyMistral-248M-v2.5

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

24.570
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

27.490
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

23.150
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

46.720
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

47.830
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.000
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

13.360
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

3.180