Instructions to use werty1248/HyperCLOVAX-1.5B-Reasoning-RFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use werty1248/HyperCLOVAX-1.5B-Reasoning-RFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="werty1248/HyperCLOVAX-1.5B-Reasoning-RFT") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("werty1248/HyperCLOVAX-1.5B-Reasoning-RFT") model = AutoModelForCausalLM.from_pretrained("werty1248/HyperCLOVAX-1.5B-Reasoning-RFT") 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
- vLLM
How to use werty1248/HyperCLOVAX-1.5B-Reasoning-RFT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/werty1248/HyperCLOVAX-1.5B-Reasoning-RFT
- SGLang
How to use werty1248/HyperCLOVAX-1.5B-Reasoning-RFT 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 "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT" \ --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": "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT", "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 "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT" \ --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": "werty1248/HyperCLOVAX-1.5B-Reasoning-RFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use werty1248/HyperCLOVAX-1.5B-Reasoning-RFT with Docker Model Runner:
docker model run hf.co/werty1248/HyperCLOVAX-1.5B-Reasoning-RFT
Update README.md
Browse files
README.md
CHANGED
|
@@ -78,9 +78,9 @@ Janetμ λ§€μΌ λμ°λ¬Ό μμ₯μμ 18λ¬λ¬λ₯Ό λ²μ΄λ€μ
λλ€. μ΄λ
|
|
| 78 |
### Rejection sampling Fine-Tuning (RFT) with least similar samples
|
| 79 |
|
| 80 |
- λͺ©ν: μ΅λν **λ€μν νμ΄ λ°©λ²**μ νμ΅νκ² λ§λλ κ²
|
| 81 |
-
1. exp-models/Open-Reasoner-Zero-orz-math-57k-collected-Koreanμ μ§λ¬Έ μ
μ€, MCQA, μ¦λͺ
μ μꡬνλ λ¬Έμ μ μΈ (54,832/56,878κ°)
|
| 82 |
-
2. HyperCLOVAX-1.5Bμ CoT ν둬ννΈλ₯Ό μΆκ°(user μ
λ ₯μ)ν ν, **Pass@8** μμ ν΅κ³Όν μ§λ¬Έλ§ μΆμΆ (10,433/54,832κ°)
|
| 83 |
-
3. HyperCLOVAX-1.5B(+CoT)λ‘ **32ν μΆκ° μΆλ‘ ** ν μ λ΅μ λ§ν λ΅λ³λ§ μΆμΆ + [Kanana-nano-2.1b](https://huggingface.co/kakaocorp/kanana-nano-2.1b-instruct)(+CoT)λ‘ **32ν μΆκ° μΆλ‘ ** ν μ λ΅μ λ§ν λ΅λ³λ§ μΆμΆ
|
| 84 |
- HyperCLOVAX-1.5B CoT Prompt: ```"μ μ κ° μ΅μ’
μ μΌλ‘ ꡬνκ³ μ νλ κ°μ΄ 무μμΈμ§ λ€μ ν λ² μ μνκ³ , λ¬Έμ μμ μ μλ 쑰건λ κΉλνκ² μ 리νμ¬ μ¬μμ±ν©λλ€. κ·Έλ¦¬κ³ λμ λ΅μ ꡬνκΈ° μν΄ κ΅¬μ²΄μ μΌλ‘ λ
Όλ¦¬ λ° μμμ μ κ°νλ©° λ¬Έμ λ₯Ό νΌ ν, μ΅μ’
λ΅λ³μ \\boxed{} μμ μμ±ν©λλ€.\n\n"```
|
| 85 |
- Kanana-2.1b CoT Prompt (λ§μ§λ§μ "μ λͺ© μμ΄ λ΄μ©λ§ μΆλ ₯ν©λλ€." μΆκ°): ```""μ μ κ° μ΅μ’
μ μΌλ‘ ꡬνκ³ μ νλ κ°μ΄ 무μμΈμ§ λ€μ ν λ² μ μνκ³ , λ¬Έμ μμ μ μλ 쑰건λ κΉλνκ² μ 리νμ¬ μ¬μμ±ν©λλ€. κ·Έλ¦¬κ³ λμ λ΅μ ꡬνκΈ° μν΄ κ΅¬μ²΄μ μΌλ‘ λ
Όλ¦¬ λ° μμμ μ κ°νλ©° λ¬Έμ λ₯Ό νΌ ν, μ΅μ’
λ΅λ³μ \\boxed{} μμ μμ±ν©λλ€. μ λͺ© μμ΄ λ΄μ©λ§ μμ±ν©λλ€.\n\n"```
|
| 86 |
|
|
|
|
| 78 |
### Rejection sampling Fine-Tuning (RFT) with least similar samples
|
| 79 |
|
| 80 |
- λͺ©ν: μ΅λν **λ€μν νμ΄ λ°©λ²**μ νμ΅νκ² λ§λλ κ²
|
| 81 |
+
1. [exp-models/Open-Reasoner-Zero-orz-math-57k-collected-Korean](https://huggingface.co/datasets/exp-models/Open-Reasoner-Zero-orz-math-57k-collected-Korean)μ μ§λ¬Έ μ
μ€, MCQA, μ¦λͺ
μ μꡬνλ λ¬Έμ μ μΈ (54,832/56,878κ°)
|
| 82 |
+
2. [HyperCLOVAX-1.5B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B)μ CoT ν둬ννΈλ₯Ό μΆκ°(user μ
λ ₯μ)ν ν, **Pass@8** μμ ν΅κ³Όν μ§λ¬Έλ§ μΆμΆ (10,433/54,832κ°)
|
| 83 |
+
3. [HyperCLOVAX-1.5B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-1.5B)(+CoT)λ‘ **32ν μΆκ° μΆλ‘ ** ν μ λ΅μ λ§ν λ΅λ³λ§ μΆμΆ + [Kanana-nano-2.1b](https://huggingface.co/kakaocorp/kanana-nano-2.1b-instruct)(+CoT)λ‘ **32ν μΆκ° μΆλ‘ ** ν μ λ΅μ λ§ν λ΅λ³λ§ μΆμΆ
|
| 84 |
- HyperCLOVAX-1.5B CoT Prompt: ```"μ μ κ° μ΅μ’
μ μΌλ‘ ꡬνκ³ μ νλ κ°μ΄ 무μμΈμ§ λ€μ ν λ² μ μνκ³ , λ¬Έμ μμ μ μλ 쑰건λ κΉλνκ² μ 리νμ¬ μ¬μμ±ν©λλ€. κ·Έλ¦¬κ³ λμ λ΅μ ꡬνκΈ° μν΄ κ΅¬μ²΄μ μΌλ‘ λ
Όλ¦¬ λ° μμμ μ κ°νλ©° λ¬Έμ λ₯Ό νΌ ν, μ΅μ’
λ΅λ³μ \\boxed{} μμ μμ±ν©λλ€.\n\n"```
|
| 85 |
- Kanana-2.1b CoT Prompt (λ§μ§λ§μ "μ λͺ© μμ΄ λ΄μ©λ§ μΆλ ₯ν©λλ€." μΆκ°): ```""μ μ κ° μ΅μ’
μ μΌλ‘ ꡬνκ³ μ νλ κ°μ΄ 무μμΈμ§ λ€μ ν λ² μ μνκ³ , λ¬Έμ μμ μ μλ 쑰건λ κΉλνκ² μ 리νμ¬ μ¬μμ±ν©λλ€. κ·Έλ¦¬κ³ λμ λ΅μ ꡬνκΈ° μν΄ κ΅¬μ²΄μ μΌλ‘ λ
Όλ¦¬ λ° μμμ μ κ°νλ©° λ¬Έμ λ₯Ό νΌ ν, μ΅μ’
λ΅λ³μ \\boxed{} μμ μμ±ν©λλ€. μ λͺ© μμ΄ λ΄μ©λ§ μμ±ν©λλ€.\n\n"```
|
| 86 |
|