Instructions to use Sumail/Ame5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sumail/Ame5 with Transformers:

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

pipe = pipeline("text-generation", model="Sumail/Ame5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sumail/Ame5")
model = AutoModelForCausalLM.from_pretrained("Sumail/Ame5")
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 Sumail/Ame5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sumail/Ame5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sumail/Ame5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sumail/Ame5

SGLang

How to use Sumail/Ame5 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 "Sumail/Ame5" \
    --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": "Sumail/Ame5",
		"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 "Sumail/Ame5" \
        --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": "Sumail/Ame5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sumail/Ame5 with Docker Model Runner:
```
docker model run hf.co/Sumail/Ame5
```

Sumail commited on Apr 16, 2024

Commit

18e1519

verified ·

1 Parent(s): 60344c8

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

README.md +5 -5
config.json +1 -1
mergekit_config.yml +3 -3
model-00001-of-00001.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model:
 - GamblerOnTrain/danke20a
-- coffie3/s32
 library_name: transformers
 tags:
 - mergekit
@@ -20,8 +20,8 @@ This model was merged using the SLERP merge method.
 ### Models Merged
 The following models were included in the merge:
 * [GamblerOnTrain/danke20a](https://huggingface.co/GamblerOnTrain/danke20a)
-* [coffie3/s32](https://huggingface.co/coffie3/s32)
 ### Configuration
@@ -33,17 +33,17 @@ slices:
   - sources:
       - model: GamblerOnTrain/danke20a
         layer_range: [0, 24]
-      - model: coffie3/s32
         layer_range: [0, 24]
 merge_method: slerp
-base_model: GamblerOnTrain/danke20a
 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: 0.35
 dtype: bfloat16
 ```

 ---
 base_model:
+- GamblerOnTrain/danke30a
 - GamblerOnTrain/danke20a
 library_name: transformers
 tags:
 - mergekit
 ### Models Merged
 The following models were included in the merge:
+* [GamblerOnTrain/danke30a](https://huggingface.co/GamblerOnTrain/danke30a)
 * [GamblerOnTrain/danke20a](https://huggingface.co/GamblerOnTrain/danke20a)
 ### Configuration
   - sources:
       - model: GamblerOnTrain/danke20a
         layer_range: [0, 24]
+      - model: GamblerOnTrain/danke30a
         layer_range: [0, 24]
 merge_method: slerp
+base_model: GamblerOnTrain/danke30a
 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
 ```

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "GamblerOnTrain/danke20a",
   "architectures": [
     "StableLmForCausalLM"
   ],

 {
+  "_name_or_path": "GamblerOnTrain/danke30a",
   "architectures": [
     "StableLmForCausalLM"
   ],

mergekit_config.yml CHANGED Viewed

@@ -3,15 +3,15 @@ slices:
   - sources:
       - model: GamblerOnTrain/danke20a
         layer_range: [0, 24]
-      - model: coffie3/s32
         layer_range: [0, 24]
 merge_method: slerp
-base_model: GamblerOnTrain/danke20a
 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: 0.35
 dtype: bfloat16

   - sources:
       - model: GamblerOnTrain/danke20a
         layer_range: [0, 24]
+      - model: GamblerOnTrain/danke30a
         layer_range: [0, 24]
 merge_method: slerp
+base_model: GamblerOnTrain/danke30a
 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

model-00001-of-00001.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8764e607696766aadef88d53e0f2df16a70e1a45237464d4390935e92d496bff
 size 3289069520

 version https://git-lfs.github.com/spec/v1
+oid sha256:14ea8a6e63440a2159477deb5b99b2c329fd45c9cca51b9d68304177cb9581b9
 size 3289069520