Instructions to use nithiyn/codestral-neuron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nithiyn/codestral-neuron with Transformers:

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

pipe = pipeline("text-generation", model="nithiyn/codestral-neuron")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nithiyn/codestral-neuron")
model = AutoModelForCausalLM.from_pretrained("nithiyn/codestral-neuron")
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 nithiyn/codestral-neuron with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nithiyn/codestral-neuron

SGLang

How to use nithiyn/codestral-neuron 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 "nithiyn/codestral-neuron" \
    --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": "nithiyn/codestral-neuron",
		"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 "nithiyn/codestral-neuron" \
        --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": "nithiyn/codestral-neuron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nithiyn/codestral-neuron with Docker Model Runner:
```
docker model run hf.co/nithiyn/codestral-neuron
```

nithiyn commited on Oct 2, 2024

Commit

1f23060

verified ·

1 Parent(s): 456f2bb

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -3

README.md CHANGED Viewed

@@ -1,3 +1,16 @@
----
-license: apache-2.0
----

+This repository contains AWS Inferentia2 and neuronx compatible checkpoints for [Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1). You can find detailed information about the base model on its [Model Card](https://huggingface.co/mistralai/Codestral-22B-v0.1).
+This model has been exported to the neuron format using specific input_shapes and compiler parameters detailed in the paragraphs below.
+It has been compiled to run on an inf2.24xlarge instance on AWS. Note that while the inf2.24xlarge has 12 cores, this compilation uses 12.
+SEQUENCE_LENGTH = 4096
+BATCH_SIZE = 4
+NUM_CORES = 12 # each inferentia chip has 2 cores, e.g. inf2.48xlarge has 12 chips or 24 cores
+PRECISION = "bf16"
+---
+license: apache-2.0
+base_model:
+- mistralai/Codestral-22B-v0.1
+---