Instructions to use fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned with Transformers:

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

pipe = pipeline("text-generation", model="fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned")

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

tokenizer = AutoTokenizer.from_pretrained("fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned")
model = AutoModelForCausalLM.from_pretrained("fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned

SGLang

How to use fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned 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 "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned" \
    --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": "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned",
		"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 "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned" \
        --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": "fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned with Docker Model Runner:
```
docker model run hf.co/fahmizainal17/Meta-Llama-3-8B-Instruct-fine-tuned
```

fahmizainal17 commited on Nov 13, 2024

Commit

40989ab

verified ·

1 Parent(s): 93b728d

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -34

README.md CHANGED Viewed

@@ -1,40 +1,20 @@
-```yaml
-library_name: transformers
-tags:
-  - language-model
-  - causal-language-model
-  - instruction-tuned
-  - advanced
-  - quantized
-datasets:
-  - custom-instruction-following-dataset
-metrics:
-  - accuracy
-  - response-quality
 license: mit
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
-pipeline_tag: text-generation
 language:
-  - en
-thumbnail: "url-to-thumbnail"
-new_version: fahmizainal17/meta-llama-3b-instruct-advanced-v2
-model-index:
-  - name: meta-llama-3b-instruct-advanced
-    results:
-      - task:
-          type: text-generation
-        dataset:
-          name: custom-instruction-following-dataset
-          type: instruction-following
-        metrics:
-          - name: Accuracy
-            value: 89.5
-        source:
-          name: Open LLM Leaderboard
-          url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
 ---
-# Model Card for fahmizainal17/meta-llama-3b-instruct-advanced
 This model is a fine-tuned version of the Meta LLaMA 3B model, optimized for instruction-based tasks such as answering questions and engaging in conversation. It has been quantized to reduce memory usage, making it more efficient for inference, especially on hardware with limited resources. This model is part of the **Advanced LLaMA Workshop** and is designed to handle complex queries and provide detailed, human-like responses.
@@ -231,4 +211,4 @@ For further inquiries, please contact fahmizainal@invokeisdata.com.
 ```
----

+---
 license: mit
 language:
+- en
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- language-model
+- causal-language-model
+- instruction-tuned
+- advanced
+- quantized
 ---
+# Model Card for fahmizainal17/Meta-Llama-3-8B-Instruct-advanced
 This model is a fine-tuned version of the Meta LLaMA 3B model, optimized for instruction-based tasks such as answering questions and engaging in conversation. It has been quantized to reduce memory usage, making it more efficient for inference, especially on hardware with limited resources. This model is part of the **Advanced LLaMA Workshop** and is designed to handle complex queries and provide detailed, human-like responses.
 ```
+---