Instructions to use Intel/tiny-random-mistral_ipex_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/tiny-random-mistral_ipex_model with Transformers:

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

pipe = pipeline("text-generation", model="Intel/tiny-random-mistral_ipex_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/tiny-random-mistral_ipex_model")
model = AutoModelForCausalLM.from_pretrained("Intel/tiny-random-mistral_ipex_model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intel/tiny-random-mistral_ipex_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Intel/tiny-random-mistral_ipex_model

SGLang

How to use Intel/tiny-random-mistral_ipex_model 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 "Intel/tiny-random-mistral_ipex_model" \
    --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": "Intel/tiny-random-mistral_ipex_model",
		"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 "Intel/tiny-random-mistral_ipex_model" \
        --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": "Intel/tiny-random-mistral_ipex_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intel/tiny-random-mistral_ipex_model with Docker Model Runner:
```
docker model run hf.co/Intel/tiny-random-mistral_ipex_model
```

Jiqing commited on Apr 30, 2025

Commit

fc1e1ec

verified ·

1 Parent(s): d2286e5

Upload 3 files

Browse files

Files changed (3) hide show

config.json +32 -0
generation_config.json +7 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "compile": false,
+  "eos_token_id": 2,
+  "head_dim": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_decoder": true,
+  "max_position_embeddings": 512,
+  "model_type": "mistral",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0c88f0e7b07956a5941a6d83bf73fd1e53269a13955ca30245a3a9c20fde9828
+size 8252717