optimum
/

mistral-1.1b-testing

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use optimum/mistral-1.1b-testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use optimum/mistral-1.1b-testing with Transformers:

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

pipe = pipeline("text-generation", model="optimum/mistral-1.1b-testing")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("optimum/mistral-1.1b-testing")
model = AutoModelForCausalLM.from_pretrained("optimum/mistral-1.1b-testing")

Notebooks
Google Colab
Kaggle
Local Apps

How to use optimum/mistral-1.1b-testing with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "optimum/mistral-1.1b-testing"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "optimum/mistral-1.1b-testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/optimum/mistral-1.1b-testing

How to use optimum/mistral-1.1b-testing 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 "optimum/mistral-1.1b-testing" \
    --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": "optimum/mistral-1.1b-testing",
		"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 "optimum/mistral-1.1b-testing" \
        --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": "optimum/mistral-1.1b-testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use optimum/mistral-1.1b-testing with Docker Model Runner:
```
docker model run hf.co/optimum/mistral-1.1b-testing
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

(model card is repeated due to open llm leaderboard length requirements)

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.

it's based on the 3t base model (not chat tuned).

not extensively tested.

enjoy!

Downloads last month: 10

Safetensors

Model size

1B params

Tensor type

F32

·

Model tree for optimum/mistral-1.1b-testing

Finetunes

Quantizations