Instructions to use Sumail/Chalice18 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sumail/Chalice18 with Transformers:

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

pipe = pipeline("text-generation", model="Sumail/Chalice18")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sumail/Chalice18")
model = AutoModelForCausalLM.from_pretrained("Sumail/Chalice18")
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 Sumail/Chalice18 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sumail/Chalice18"
# 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/Chalice18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sumail/Chalice18

SGLang

How to use Sumail/Chalice18 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/Chalice18" \
    --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/Chalice18",
		"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/Chalice18" \
        --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/Chalice18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sumail/Chalice18 with Docker Model Runner:
```
docker model run hf.co/Sumail/Chalice18
```

Sumail commited on May 16, 2024

Commit

e18d0af

verified ·

1 Parent(s): e2ad954

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

README.md +4 -4
config.json +1 -1
mergekit_config.yml +2 -2
model-00001-of-00001.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model:
 - rwh/s1_1712781243
-- abc88767/22c75
 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:
 * [rwh/s1_1712781243](https://huggingface.co/rwh/s1_1712781243)
-* [abc88767/22c75](https://huggingface.co/abc88767/22c75)
 ### Configuration
@@ -33,10 +33,10 @@ slices:
   - sources:
       - model: rwh/s1_1712781243
         layer_range: [0, 24]
-      - model: abc88767/22c75
         layer_range: [0, 24]
 merge_method: slerp
-base_model: abc88767/22c75
 parameters:
   t:
     - filter: self_attn

 ---
 base_model:
+- abc88767/2c75
 - rwh/s1_1712781243
 library_name: transformers
 tags:
 - mergekit
 ### Models Merged
 The following models were included in the merge:
+* [abc88767/2c75](https://huggingface.co/abc88767/2c75)
 * [rwh/s1_1712781243](https://huggingface.co/rwh/s1_1712781243)
 ### Configuration
   - sources:
       - model: rwh/s1_1712781243
         layer_range: [0, 24]
+      - model: abc88767/2c75
         layer_range: [0, 24]
 merge_method: slerp
+base_model: abc88767/2c75
 parameters:
   t:
     - filter: self_attn

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "abc88767/22c75",
   "architectures": [
     "StableLmForCausalLM"
   ],

 {
+  "_name_or_path": "abc88767/2c75",
   "architectures": [
     "StableLmForCausalLM"
   ],

mergekit_config.yml CHANGED Viewed

@@ -3,10 +3,10 @@ slices:
   - sources:
       - model: rwh/s1_1712781243
         layer_range: [0, 24]
-      - model: abc88767/22c75
         layer_range: [0, 24]
 merge_method: slerp
-base_model: abc88767/22c75
 parameters:
   t:
     - filter: self_attn

   - sources:
       - model: rwh/s1_1712781243
         layer_range: [0, 24]
+      - model: abc88767/2c75
         layer_range: [0, 24]
 merge_method: slerp
+base_model: abc88767/2c75
 parameters:
   t:
     - filter: self_attn

model-00001-of-00001.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1167ad85041ae1352575e83677bdccbeb49e4b0f565fc1c6687e6142598243bf
 size 3289069520

 version https://git-lfs.github.com/spec/v1
+oid sha256:339df45ee76ecd981d85a14b75e1f3e037d2c55f180322cb4ebb17aba535880c
 size 3289069520