Instructions to use prince-canuma/Damysus-2.7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prince-canuma/Damysus-2.7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="prince-canuma/Damysus-2.7B-Chat", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prince-canuma/Damysus-2.7B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("prince-canuma/Damysus-2.7B-Chat", trust_remote_code=True, device_map="auto")
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 prince-canuma/Damysus-2.7B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prince-canuma/Damysus-2.7B-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prince-canuma/Damysus-2.7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prince-canuma/Damysus-2.7B-Chat

SGLang

How to use prince-canuma/Damysus-2.7B-Chat 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 "prince-canuma/Damysus-2.7B-Chat" \
    --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": "prince-canuma/Damysus-2.7B-Chat",
		"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 "prince-canuma/Damysus-2.7B-Chat" \
        --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": "prince-canuma/Damysus-2.7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prince-canuma/Damysus-2.7B-Chat with Docker Model Runner:
```
docker model run hf.co/prince-canuma/Damysus-2.7B-Chat
```

prince-canuma commited on Feb 17, 2024

Commit

6f1d321

verified ·

1 Parent(s): 728223f

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -8

README.md CHANGED Viewed

@@ -30,9 +30,12 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: ARC
-            type: acc
             value: 59.81
             verified: true
         source:
@@ -41,8 +44,11 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: Hellaswag
             type: acc
             value: 74.52
             verified: true
@@ -52,8 +58,11 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: MMLU
             type: acc
             value: 56.33
             verified: true
@@ -63,9 +72,12 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: Truthful QA
-            type: acc
             value: 46.74
             verified: true
         source:
@@ -74,8 +86,11 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: Winogrande
             type: acc
             value: 75.06
             verified: true
@@ -85,8 +100,11 @@ model-index:
       - task:
           type: text-generation
         metrics:
-          - name: GSM8K
             type: acc
             value: 50.64
             verified: true

       - task:
           type: text-generation
+        dataset:
+          name: ARC (25-shot)
+          type: ai2_arc
         metrics:
+          - name: Accuracy Norm
+            type: acc_norm
             value: 59.81
             verified: true
         source:
       - task:
           type: text-generation
+        dataset:
+          name: Hellaswag (10-shot)
+          type: Hellaswag
         metrics:
+          - name: Accuracy Norm
             type: acc
             value: 74.52
             verified: true
       - task:
           type: text-generation
+        dataset:
+          name: MMLU (5-shot)
+          type: MMLU
         metrics:
+          - name: Accuracy
             type: acc
             value: 56.33
             verified: true
       - task:
           type: text-generation
+        dataset:
+          name: Truthful QA
+          type: Truthful_QA
         metrics:
+          - name: Multi-true
+            type: mc2
             value: 46.74
             verified: true
         source:
       - task:
           type: text-generation
+        dataset:
+          name: Winogrande (5-shot)
+          type: Winogrande
         metrics:
+          - name: Accuracy
             type: acc
             value: 75.06
             verified: true
       - task:
           type: text-generation
+        dataset:
+          name: GSM8K (5-shot)
+          type: GSM8K
         metrics:
+          - name: Accuracy
             type: acc
             value: 50.64
             verified: true