Instructions to use Chickaboo/fine-mixtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chickaboo/fine-mixtral with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Chickaboo/fine-mixtral")
model = AutoModelForCausalLM.from_pretrained("Chickaboo/fine-mixtral", device_map="auto")
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 Settings

vLLM

How to use Chickaboo/fine-mixtral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Chickaboo/fine-mixtral

SGLang

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

Docker Model Runner
How to use Chickaboo/fine-mixtral with Docker Model Runner:
```
docker model run hf.co/Chickaboo/fine-mixtral
```

Chickaboo commited on May 9, 2024

Commit

707db42

verified ·

1 Parent(s): 87c519c

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -64,15 +64,15 @@ These are the Benchmark results for Chicka-Mixtral-3x7b compared to other flagsh
 ### Open LLM Leaderboards
-| Benchmark    | Chicka-Mixtral-3X7B  | Mistral-7B-Instruct-v0.2 | Meta-Llama-3-8B |
 |--------------|----------------------|--------------------------|-----------------|
-| Average      | 69.19                |  60.97                   | 62.55           |
-| ARC          | 64.08                |  59.98                   | 59.47           |
-| Hellaswag    | 83.96                |  83.31                   | 82.09           |
-| MMLU         | 64.87                |  64.16                   | 66.67           |
-| TruthfulQA   | 50.51                |  42.15                   | 43.95           |
-| Winogrande   | 81.06                |  78.37                   | 77.35           |
-| GSM8K        | 70.66                |  37.83                   | 45.79           |
 ### Usage

 ### Open LLM Leaderboards
+| **Benchmark**    | **Chicka-Mixtral-3X7B**  | **Mistral-7B-Instruct-v0.2** | **Meta-Llama-3-8B** |
 |--------------|----------------------|--------------------------|-----------------|
+| **Average**      | **69.19**                |  60.97                   | 62.55           |
+| **ARC**          | **64.08**                |  59.98                   | 59.47           |
+| **Hellaswag**    | **83.96**                |  83.31                   | 82.09           |
+| **MMLU**         | 64.87                |  64.16                   | **66.67**           |
+| **TruthfulQA**   | **50.51**                |  42.15                   | 43.95           |
+| **Winogrande**   | **81.06**                |  78.37                   | 77.35           |
+| **GSM8K**        | **70.66**                |  37.83                   | 45.79           |
 ### Usage