Instructions to use distilabel-internal-testing/tiny-random-mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distilabel-internal-testing/tiny-random-mistral with Transformers:

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

pipe = pipeline("text-generation", model="distilabel-internal-testing/tiny-random-mistral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("distilabel-internal-testing/tiny-random-mistral")
model = AutoModelForCausalLM.from_pretrained("distilabel-internal-testing/tiny-random-mistral")
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

vLLM

How to use distilabel-internal-testing/tiny-random-mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/distilabel-internal-testing/tiny-random-mistral

SGLang

How to use distilabel-internal-testing/tiny-random-mistral 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 "distilabel-internal-testing/tiny-random-mistral" \
    --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": "distilabel-internal-testing/tiny-random-mistral",
		"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 "distilabel-internal-testing/tiny-random-mistral" \
        --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": "distilabel-internal-testing/tiny-random-mistral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use distilabel-internal-testing/tiny-random-mistral with Docker Model Runner:
```
docker model run hf.co/distilabel-internal-testing/tiny-random-mistral
```

alvarobartt HF Staff commited on Mar 20, 2024

Commit

bc0c205

verified ·

1 Parent(s): 8ab12fc

Upload MistralForCausalLM

Browse files

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -6,10 +6,10 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "max_position_embeddings": 512,
   "model_type": "mistral",
   "num_attention_heads": 1,
   "num_hidden_layers": 1,

   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
+  "hidden_size": 128,
   "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "max_position_embeddings": 128,
   "model_type": "mistral",
   "num_attention_heads": 1,
   "num_hidden_layers": 1,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c3f0efb6c285418bad4633031057a8ba0ba85bc7c42dd36ac758db21502303
-size 138419480

 version https://git-lfs.github.com/spec/v1
+oid sha256:f4de1f8ae7fbf6cfa4c8b941655105379786f62b18234afe66bf8713cb533c68
+size 33229576