Instructions to use roger33303/llama3.2-3b-Instruct-Finetune-website-QnA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roger33303/llama3.2-3b-Instruct-Finetune-website-QnA with Transformers:

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

pipe = pipeline("text-generation", model="roger33303/llama3.2-3b-Instruct-Finetune-website-QnA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("roger33303/llama3.2-3b-Instruct-Finetune-website-QnA")
model = AutoModelForCausalLM.from_pretrained("roger33303/llama3.2-3b-Instruct-Finetune-website-QnA", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use roger33303/llama3.2-3b-Instruct-Finetune-website-QnA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/roger33303/llama3.2-3b-Instruct-Finetune-website-QnA

SGLang

How to use roger33303/llama3.2-3b-Instruct-Finetune-website-QnA 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 "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA" \
    --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": "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA",
		"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 "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA" \
        --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": "roger33303/llama3.2-3b-Instruct-Finetune-website-QnA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use roger33303/llama3.2-3b-Instruct-Finetune-website-QnA with Docker Model Runner:
```
docker model run hf.co/roger33303/llama3.2-3b-Instruct-Finetune-website-QnA
```

roger33303 commited on Nov 13, 2024

Commit

fface54

verified ·

1 Parent(s): df0fa93

Final Update in evaluation metrics

Browse files

Files changed (1) hide show

README.md +1 -62

README.md CHANGED Viewed

@@ -23,6 +23,7 @@ model-index:
     - name: SACREBLEU
       type: sacrebleu
       value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
@@ -34,18 +35,6 @@ model-index:
     - name: CER_SCORE
       type: cer_score
       value: 0.137935
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Custom
-      type: Custom
-      split: test
-    metrics:
-    - name: SACREBLEU
-      type: sacrebleu
-      value: 85.979319
   - task:
       type: text-generation
@@ -59,17 +48,6 @@ model-index:
       type: meteor
       value: 0.903607
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Custom
-      type: Custom
-      split: test
-    metrics:
-    - name: SACREBLEU
-      type: sacrebleu
-      value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
@@ -82,17 +60,6 @@ model-index:
       type: rouge1
       value: 0.904733
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Custom
-      type: Custom
-      split: test
-    metrics:
-    - name: SACREBLEU
-      type: sacrebleu
-      value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
@@ -105,17 +72,6 @@ model-index:
       type: rouge2
       value: 0.867881
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Custom
-      type: Custom
-      split: test
-    metrics:
-    - name: SACREBLEU
-      type: sacrebleu
-      value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
@@ -128,17 +84,6 @@ model-index:
       type: rougeL
       value: 0.905276
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Custom
-      type: Custom
-      split: test
-    metrics:
-    - name: SACREBLEU
-      type: sacrebleu
-      value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
@@ -150,12 +95,6 @@ model-index:
     - name: ROUGELSUM
       type: rougeLsum
       value: 0.904084
 ---

     - name: SACREBLEU
       type: sacrebleu
       value: 85.979319
   - task:
       type: text-generation
       name: Text Generation
     - name: CER_SCORE
       type: cer_score
       value: 0.137935
   - task:
       type: text-generation
       type: meteor
       value: 0.903607
   - task:
       type: text-generation
       name: Text Generation
       type: rouge1
       value: 0.904733
   - task:
       type: text-generation
       name: Text Generation
       type: rouge2
       value: 0.867881
   - task:
       type: text-generation
       name: Text Generation
       type: rougeL
       value: 0.905276
   - task:
       type: text-generation
       name: Text Generation
     - name: ROUGELSUM
       type: rougeLsum
       value: 0.904084
 ---