Instructions to use automerger/YamshadowExperiment28-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use automerger/YamshadowExperiment28-7B with Transformers:

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

pipe = pipeline("text-generation", model="automerger/YamshadowExperiment28-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("automerger/YamshadowExperiment28-7B")
model = AutoModelForCausalLM.from_pretrained("automerger/YamshadowExperiment28-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use automerger/YamshadowExperiment28-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "automerger/YamshadowExperiment28-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "automerger/YamshadowExperiment28-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/automerger/YamshadowExperiment28-7B

SGLang

How to use automerger/YamshadowExperiment28-7B 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 "automerger/YamshadowExperiment28-7B" \
    --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": "automerger/YamshadowExperiment28-7B",
		"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 "automerger/YamshadowExperiment28-7B" \
        --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": "automerger/YamshadowExperiment28-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use automerger/YamshadowExperiment28-7B with Docker Model Runner:
```
docker model run hf.co/automerger/YamshadowExperiment28-7B
```

Update README.md

by mlabonne - opened Apr 8, 2024

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+32

-2

Files changed (1) hide show

README.md +32 -2

README.md CHANGED Viewed

@@ -10,16 +10,46 @@ base_model:
 - yam-peleg/Experiment28-7B
 ---
-# YamshadowExperiment28-7B
 YamshadowExperiment28-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
 * [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
 * [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B)
-**YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24). I don't recommend using it because of issues that are not reflected in the benchmarks.**
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ONmehD2GXYefb-O3zHbp5.png)
 ## 🧩 Configuration
 ```yaml

 - yam-peleg/Experiment28-7B
 ---
+# 🧪 YamshadowExperiment28-7B
 YamshadowExperiment28-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
 * [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
 * [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B)
+## 🔍 Applications
+This model uses a context window of 8k. I recommend using it with the Alpaca chat template (works perfectly with LM Studio).
+The model can sometimes break and output a lot of "INST". From my experience, its excellent results on the Open LLM Leaderboard are probably a sign of overfitting.
+## ⚡ Quantized models
+* **GGUF**: https://huggingface.co/automerger/YamshadowExperiment28-7B-GGUF
+## 🏆 Evaluation
+### Open LLM Leaderboard
+YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24).
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ONmehD2GXYefb-O3zHbp5.png)
+### EQ-bench
+Thanks to [Samuel J. Paech](https://twitter.com/sam_paech), who kindly ran the evaluation.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/e6cg_7TD35JveTjx_KoTT.png)
+### Nous
+Evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/s4oKdK3FfaDsagXe7tEM2.png)
+## 🌳 Model Family Tree
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/fEA4EdtSa_fssdvsUXPf1.png)
 ## 🧩 Configuration
 ```yaml