Text Generation
Transformers
Safetensors
Rust
English
Russian
qwen2
code
conversational
text-generation-inference
Instructions to use maylore-ai/Temper-2-Axon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maylore-ai/Temper-2-Axon with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="maylore-ai/Temper-2-Axon") 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("maylore-ai/Temper-2-Axon") model = AutoModelForCausalLM.from_pretrained("maylore-ai/Temper-2-Axon", 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 maylore-ai/Temper-2-Axon with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maylore-ai/Temper-2-Axon" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maylore-ai/Temper-2-Axon", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/maylore-ai/Temper-2-Axon
- SGLang
How to use maylore-ai/Temper-2-Axon 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 "maylore-ai/Temper-2-Axon" \ --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": "maylore-ai/Temper-2-Axon", "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 "maylore-ai/Temper-2-Axon" \ --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": "maylore-ai/Temper-2-Axon", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use maylore-ai/Temper-2-Axon with Docker Model Runner:
docker model run hf.co/maylore-ai/Temper-2-Axon
Clarify that the hard tasks declare their own macros
Browse files
README.md
CHANGED
|
@@ -67,7 +67,7 @@ A GGUF version for llama.cpp, LM Studio and Ollama is in [maylore-ai/Temper-2-Ax
|
|
| 67 |
|
| 68 |
## Limitations
|
| 69 |
|
| 70 |
-
Axon trails larger models, with Qwen2.5-Coder-7B solving 8.2 points more HumanEval-RS tasks on the first try and Qwen3.5-9B 11.8 more. The model rarely solves tasks
|
| 71 |
|
| 72 |
## License
|
| 73 |
|
|
|
|
| 67 |
|
| 68 |
## Limitations
|
| 69 |
|
| 70 |
+
Axon trails larger models, with Qwen2.5-Coder-7B solving 8.2 points more HumanEval-RS tasks on the first try and Qwen3.5-9B 11.8 more. The model rarely solves tasks that declare their own macros, use lifetimes or async code. Having been trained on chat requests without fill-in-the-middle, it does not work as a drop-in model for inline completion in an editor.
|
| 71 |
|
| 72 |
## License
|
| 73 |
|