Instructions to use birgermoell/NeuralBeagle-Flashback with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use birgermoell/NeuralBeagle-Flashback with Transformers:

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

pipe = pipeline("text-generation", model="birgermoell/NeuralBeagle-Flashback")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("birgermoell/NeuralBeagle-Flashback")
model = AutoModelForCausalLM.from_pretrained("birgermoell/NeuralBeagle-Flashback")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use birgermoell/NeuralBeagle-Flashback with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/birgermoell/NeuralBeagle-Flashback

SGLang

How to use birgermoell/NeuralBeagle-Flashback 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 "birgermoell/NeuralBeagle-Flashback" \
    --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": "birgermoell/NeuralBeagle-Flashback",
		"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 "birgermoell/NeuralBeagle-Flashback" \
        --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": "birgermoell/NeuralBeagle-Flashback",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use birgermoell/NeuralBeagle-Flashback with Docker Model Runner:
```
docker model run hf.co/birgermoell/NeuralBeagle-Flashback
```

birgermoell commited on Jan 30, 2024

Commit

4792cd8

verified ·

1 Parent(s): a65787c

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +12 -19

README.md CHANGED Viewed

@@ -3,38 +3,31 @@ tags:
 - merge
 - mergekit
 - lazymergekit
-- timpal0l/Mistral-7B-v0.1-flashback-v2
 - mlabonne/NeuralBeagle14-7B
 base_model:
-- timpal0l/Mistral-7B-v0.1-flashback-v2
 - mlabonne/NeuralBeagle14-7B
 ---
 # NeuralBeagle-Flashback
 NeuralBeagle-Flashback is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [timpal0l/Mistral-7B-v0.1-flashback-v2](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2)
 * [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
 ## 🧩 Configuration
 ```yaml
-slices:
-  - sources:
-      - model: timpal0l/Mistral-7B-v0.1-flashback-v2
-        layer_range: [0, 32]
-      - model: mlabonne/NeuralBeagle14-7B
-        layer_range: [0, 32]
-merge_method: slerp
-base_model: timpal0l/Mistral-7B-v0.1-flashback-v2
-parameters:
-  t:
-    - filter: self_attn
-      value: [0, 0.5, 0.3, 0.7, 1]
-    - filter: mlp
-      value: [1, 0.5, 0.7, 0.3, 0]
-    - value: 0.5
-dtype: bfloat16
 ```
 ## 💻 Usage

 - merge
 - mergekit
 - lazymergekit
 - mlabonne/NeuralBeagle14-7B
 base_model:
 - mlabonne/NeuralBeagle14-7B
 ---
 # NeuralBeagle-Flashback
 NeuralBeagle-Flashback is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
 ## 🧩 Configuration
 ```yaml
+  models:
+    - model: timpal0l/Mistral-7B-v0.1-flashback-v2
+      # No parameters necessary for base model
+    - model: mlabonne/NeuralBeagle14-7B
+      parameters:
+        density: 0.53
+        weight: 0.6
+  merge_method: dare_ties
+  base_model: timpal0l/Mistral-7B-v0.1-flashback-v2
+  parameters:
+    int8_mask: true
+  dtype: bfloat16
 ```
 ## 💻 Usage