Instructions to use ledat1205/mistral-instruct-v2-2k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ledat1205/mistral-instruct-v2-2k with Transformers:

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

pipe = pipeline("text-generation", model="ledat1205/mistral-instruct-v2-2k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ledat1205/mistral-instruct-v2-2k")
model = AutoModelForCausalLM.from_pretrained("ledat1205/mistral-instruct-v2-2k", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ledat1205/mistral-instruct-v2-2k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ledat1205/mistral-instruct-v2-2k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ledat1205/mistral-instruct-v2-2k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ledat1205/mistral-instruct-v2-2k

SGLang

How to use ledat1205/mistral-instruct-v2-2k 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 "ledat1205/mistral-instruct-v2-2k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ledat1205/mistral-instruct-v2-2k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ledat1205/mistral-instruct-v2-2k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ledat1205/mistral-instruct-v2-2k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ledat1205/mistral-instruct-v2-2k with Docker Model Runner:
```
docker model run hf.co/ledat1205/mistral-instruct-v2-2k
```

transformers

This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.3956

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: 0.0002
train_batch_size: 48
eval_batch_size: 12
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 74
training_steps: 743

Training results

Training Loss	Epoch	Step	Validation Loss
0.2297	1.8	74	0.4019
0.1551	3.61	148	0.4087
0.1306	5.41	222	0.4018
0.0894	7.22	296	0.3998
0.0799	9.02	370	0.3972
0.0782	10.83	444	0.3965
0.0748	12.63	518	0.3967
0.0617	14.44	592	0.3964
0.0666	16.24	666	0.3956
0.0753	18.05	740	0.3956

Framework versions

Transformers 4.39.2
Pytorch 2.1.0+cu118
Datasets 2.16.0
Tokenizers 0.15.2

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

F32