Instructions to use PAIXAI/Astrid-7b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PAIXAI/Astrid-7b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="PAIXAI/Astrid-7b-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PAIXAI/Astrid-7b-Instruct")
model = AutoModelForCausalLM.from_pretrained("PAIXAI/Astrid-7b-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PAIXAI/Astrid-7b-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PAIXAI/Astrid-7b-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PAIXAI/Astrid-7b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PAIXAI/Astrid-7b-Instruct

SGLang

How to use PAIXAI/Astrid-7b-Instruct 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 "PAIXAI/Astrid-7b-Instruct" \
    --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": "PAIXAI/Astrid-7b-Instruct",
		"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 "PAIXAI/Astrid-7b-Instruct" \
        --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": "PAIXAI/Astrid-7b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PAIXAI/Astrid-7b-Instruct with Docker Model Runner:
```
docker model run hf.co/PAIXAI/Astrid-7b-Instruct
```

Stevross commited on Nov 3, 2023

Commit

4aef56b

1 Parent(s): bfc5b09

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -8

README.md CHANGED Viewed

@@ -6,16 +6,24 @@ tags:
 - gpt
 - llm
 - large language model
-- h2o-llmstudio
-inference: false
-thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
 ---
 # Model Card
 ## Summary
-This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
 - Base model: [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
 ## Usage
@@ -37,7 +45,7 @@ Also make sure you are providing your huggingface token to the pipeline if the m
 from transformers import pipeline
 generate_text = pipeline(
-    model="Stevross/Astrid-7b-Instruct",
     torch_dtype="auto",
     trust_remote_code=True,
     use_fast=True,
@@ -75,13 +83,13 @@ from h2oai_pipeline import H2OTextGenerationPipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer
 tokenizer = AutoTokenizer.from_pretrained(
-    "Stevross/Astrid-7b-Instruct",
     use_fast=True,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
-    "Stevross/Astrid-7b-Instruct",
     torch_dtype="auto",
     device_map={"": "cuda:0"},
     trust_remote_code=True,
@@ -107,7 +115,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_name = "Stevross/Astrid-7b-Instruct"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "<|prompt|>How are you?</s><|answer|>"

 - gpt
 - llm
 - large language model
+- PAIX.Cloud
+inference: true
+thumbnail: https://static.wixstatic.com/media/bdee4e_8aa5cefc86024bc88f7e20e3e19d9ff3~mv2.png/v1/fill/w_192%2Ch_192%2Clg_1%2Cusm_0.66_1.00_0.01/bdee4e_8aa5cefc86024bc88f7e20e3e19d9ff3~mv2.png
 ---
 # Model Card
 ## Summary
 - Base model: [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
+This model, Astrid-1B, is a Mistral-7B model for causal language modeling, designed to generate human-like text.
+It's part of our mission to make AI technology accessible to everyone, focusing on personalization, data privacy, and transparent AI governance.
+Trained in English, it's a versatile tool for a variety of applications.
+This model is one of the many models available on our platform, and we currently have a 1B and 7B open-source model.
+This model was trained by [PAIX.Cloud](https://www.paix.cloud/).
+- Wait list: [Wait List](https://www.paix.cloud/join-waitlist)
 ## Usage
 from transformers import pipeline
 generate_text = pipeline(
+    model="PAIXAI/Astrid-7b-Instruct",
     torch_dtype="auto",
     trust_remote_code=True,
     use_fast=True,
 from transformers import AutoModelForCausalLM, AutoTokenizer
 tokenizer = AutoTokenizer.from_pretrained(
+    "PAIXAI/Astrid-7b-Instruct",
     use_fast=True,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
+    "PAIXAI/Astrid-7b-Instruct",
     torch_dtype="auto",
     device_map={"": "cuda:0"},
     trust_remote_code=True,
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "PAIXAI/Astrid-7b-Instruct"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "<|prompt|>How are you?</s><|answer|>"