Instructions to use KnutJaegersberg/MistralInstructLongish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/MistralInstructLongish with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/MistralInstructLongish", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/MistralInstructLongish", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/MistralInstructLongish", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/MistralInstructLongish with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/KnutJaegersberg/MistralInstructLongish

SGLang

How to use KnutJaegersberg/MistralInstructLongish 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 "KnutJaegersberg/MistralInstructLongish" \
    --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": "KnutJaegersberg/MistralInstructLongish",
		"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 "KnutJaegersberg/MistralInstructLongish" \
        --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": "KnutJaegersberg/MistralInstructLongish",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KnutJaegersberg/MistralInstructLongish with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/MistralInstructLongish
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

It was trained for like 3 epochs on a merger dataset of several instruction datasets, with partially longer instructions.

Alpaca Prompt Format:

### Instruction:
blablabla
### Input: 
(optional)
### Response:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	48.99
ARC (25-shot)	60.75
HellaSwag (10-shot)	81.86
MMLU (5-shot)	60.49
TruthfulQA (0-shot)	40.55
Winogrande (5-shot)	76.56
GSM8K (5-shot)	1.52
DROP (3-shot)	21.22

Downloads last month: 415

Safetensors

Model size

7B params

Tensor type

F16

Model tree for KnutJaegersberg/MistralInstructLongish

Quantizations

2 models

KnutJaegersberg
/

MistralInstructLongish

Open LLM Leaderboard Evaluation Results

Model tree for KnutJaegersberg/MistralInstructLongish

Dataset used to train KnutJaegersberg/MistralInstructLongish

Spaces using KnutJaegersberg/MistralInstructLongish 9