Instructions to use R136a1/BeyondInfinity-4x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use R136a1/BeyondInfinity-4x7B with Transformers:

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

pipe = pipeline("text-generation", model="R136a1/BeyondInfinity-4x7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("R136a1/BeyondInfinity-4x7B")
model = AutoModelForCausalLM.from_pretrained("R136a1/BeyondInfinity-4x7B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use R136a1/BeyondInfinity-4x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "R136a1/BeyondInfinity-4x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "R136a1/BeyondInfinity-4x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/R136a1/BeyondInfinity-4x7B

SGLang

How to use R136a1/BeyondInfinity-4x7B 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 "R136a1/BeyondInfinity-4x7B" \
    --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": "R136a1/BeyondInfinity-4x7B",
		"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 "R136a1/BeyondInfinity-4x7B" \
        --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": "R136a1/BeyondInfinity-4x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use R136a1/BeyondInfinity-4x7B with Docker Model Runner:
```
docker model run hf.co/R136a1/BeyondInfinity-4x7B
```

R136a1 commited on May 16, 2024

Commit

8b85303

verified ·

1 Parent(s): 31238b2

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -19

README.md CHANGED Viewed

@@ -6,24 +6,14 @@ tags:
 - safetensors
 - mixtral
 ---
-Test model.
-Under testing...
-Recipe:
-```yaml
-base_model: /content/InfinityRP
-gate_mode: random
-dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
-## (optional)
-experts_per_token: 2
-experts:
-  - source_model: /content/WestLake
-    positive_prompts: []
-  - source_model: /content/Kuno
-    positive_prompts: []
-  - source_model: /content/InfinityRP
-    positive_prompts: []
-  - source_model: /content/LemonadeRP
-    positive_prompts: []
-```

 - safetensors
 - mixtral
 ---
+Testing done.
+It performs really well in complex scenario and follows the character card quite well. The char card and previous message can affect a lot to the next reply style.
+The main idea is instead of _merging_ models to create new model, I try to put these best model into mixtral so it can work together. And the result is good, every model has its uniqueness and strength.
+Downside? it only support 8k (8192) context length...
+Alpaca prompting format.