Text Generation
Transformers
Safetensors
PEFT
English
llama
llama-3
finetuned
cyber-security
reasoning
instruction-tuning
lora
conversational
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use OpenPathAI/Orbit-3-8B-Llama-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenPathAI/Orbit-3-8B-Llama-thinking") 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("OpenPathAI/Orbit-3-8B-Llama-thinking") model = AutoModelForCausalLM.from_pretrained("OpenPathAI/Orbit-3-8B-Llama-thinking", 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]:])) - PEFT
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenPathAI/Orbit-3-8B-Llama-thinking" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenPathAI/Orbit-3-8B-Llama-thinking", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OpenPathAI/Orbit-3-8B-Llama-thinking
- SGLang
How to use OpenPathAI/Orbit-3-8B-Llama-thinking 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 "OpenPathAI/Orbit-3-8B-Llama-thinking" \ --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": "OpenPathAI/Orbit-3-8B-Llama-thinking", "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 "OpenPathAI/Orbit-3-8B-Llama-thinking" \ --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": "OpenPathAI/Orbit-3-8B-Llama-thinking", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with Docker Model Runner:
docker model run hf.co/OpenPathAI/Orbit-3-8B-Llama-thinking
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,8 +57,6 @@ Model ini dirancang khusus untuk:
|
|
| 57 |
|
| 58 |
| Parameter | Nilai |
|
| 59 |
|-----------|-------|
|
| 60 |
-
| Dataset | `echel0nn1881/kimi-cyber-reasoning` |
|
| 61 |
-
| Ukuran Dataset | 997 sampel |
|
| 62 |
| Epoch Pelatihan | 3 |
|
| 63 |
| Metode Fine-tuning | LoRA (Low-Rank Adaptation) |
|
| 64 |
| Presisi | FP16 |
|
|
@@ -197,20 +195,11 @@ Kasus Penggunaan
|
|
| 197 |
|
| 198 |
Penggunaan yang Disarankan
|
| 199 |
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
Keterbatasan
|
| 207 |
-
|
| 208 |
-
Keterbatasan Deskripsi
|
| 209 |
-
Spesialisasi Domain Dioptimalkan untuk keamanan siber, mungkin kurang optimal di domain lain
|
| 210 |
-
Akurasi Mungkin menghasilkan informasi yang tidak akurat atau usang
|
| 211 |
-
Saran Kritis Tidak cocok untuk keputusan keamanan kritis tanpa tinjauan manusia
|
| 212 |
-
Bias Mungkin mencerminkan bias yang ada dalam data pelatihan
|
| 213 |
-
Bahasa Utamanya Inggris dan Indonesia
|
| 214 |
|
| 215 |
---
|
| 216 |
|
|
|
|
| 57 |
|
| 58 |
| Parameter | Nilai |
|
| 59 |
|-----------|-------|
|
|
|
|
|
|
|
| 60 |
| Epoch Pelatihan | 3 |
|
| 61 |
| Metode Fine-tuning | LoRA (Low-Rank Adaptation) |
|
| 62 |
| Presisi | FP16 |
|
|
|
|
| 195 |
|
| 196 |
Penggunaan yang Disarankan
|
| 197 |
|
| 198 |
+
- Pendidikan dan pelatihan keamanan siber
|
| 199 |
+
- Pembuatan dokumentasi keamanan
|
| 200 |
+
- Tinjauan kode dan bantuan penulisan kode aman
|
| 201 |
+
- Analisis intelijen ancaman
|
| 202 |
+
- Rekomendasi praktik terbaik keamanan
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
|
| 204 |
---
|
| 205 |
|