Instructions to use solidrust/Mixtral_AI_MiniTron_Chat-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Mixtral_AI_MiniTron_Chat-AWQ with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Mixtral_AI_MiniTron_Chat-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Mixtral_AI_MiniTron_Chat-AWQ")
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 solidrust/Mixtral_AI_MiniTron_Chat-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/solidrust/Mixtral_AI_MiniTron_Chat-AWQ

SGLang

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

Docker Model Runner
How to use solidrust/Mixtral_AI_MiniTron_Chat-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Mixtral_AI_MiniTron_Chat-AWQ
```

Suparious commited on Apr 19, 2024

Commit

1f981c4

verified ·

1 Parent(s): 1d3b2df

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -2

README.md CHANGED Viewed

@@ -10,6 +10,24 @@ pipeline_tag: text-generation
 inference: false
 quantized_by: Suparious
 ---
-#
-**UPLOAD IN PROGRESS**

 inference: false
 quantized_by: Suparious
 ---
+# LeroyDyer/Mixtral_AI_MiniTron_Chat AWQ
+- Model creator: [LeroyDyer](https://huggingface.co/LeroyDyer)
+- Original model: [Mixtral_AI_MiniTron_Chat](https://huggingface.co/LeroyDyer/Mixtral_AI_MiniTron_Chat)
+## Model Summary
+these little one are easy to train for task !!! ::
+They already have some training (not great)
+But they can take more and more
+(and being MISTRAL they can takes lora modules!)
+Rememeber to add training on to the lora you merge withit : ie load the lora and train a few cycle on the same data that was applied in the p=lora (ie 20 Steps ) and
+See it it took hold then merge IT!
+- **Developed by:** LeroyDyer
+- **License:** apache-2.0
+- **Finetuned from model :** LeroyDyer/Mixtral_AI_MiniTron