Instructions to use CohereLabs/command-a-translate-08-2025 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CohereLabs/command-a-translate-08-2025 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CohereLabs/command-a-translate-08-2025") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CohereLabs/command-a-translate-08-2025") model = AutoModelForCausalLM.from_pretrained("CohereLabs/command-a-translate-08-2025") 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]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CohereLabs/command-a-translate-08-2025 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CohereLabs/command-a-translate-08-2025" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CohereLabs/command-a-translate-08-2025", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/CohereLabs/command-a-translate-08-2025
- SGLang
How to use CohereLabs/command-a-translate-08-2025 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 "CohereLabs/command-a-translate-08-2025" \ --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": "CohereLabs/command-a-translate-08-2025", "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 "CohereLabs/command-a-translate-08-2025" \ --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": "CohereLabs/command-a-translate-08-2025", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use CohereLabs/command-a-translate-08-2025 with Docker Model Runner:
docker model run hf.co/CohereLabs/command-a-translate-08-2025
The model translates the text into the wrong language
As a user, I expect the text to be translated into Ukrainian, but it is actually translated into Russian. I am experiencing the same result when using the Playground and the SDK as well. P.S.: The phrase Translate everything that follows into was taken from the documentation.
Prompt:
Translate everything that follows into Ukrainian:
Xenia and Sergey play the following game. Xenia thinks of a positive integer $N$ not exceeding 5000. Then she fixes 20 distinct positive integers $a_{1}, a_{2}, \\ldots, a_{20}$ such that, for each $k=1,2, \\ldots, 20$, the numbers $N$ and $a_{k}$ are congruent modulo $k$. By a move, Sergey tells Xenia a set $S$ of positive integers not exceeding 20 , and she tells him back the set $\\left\\{a_{k}: k \\in S\\right\\}$ without spelling out which number corresponds to which index. How many moves does Sergey need to determine for sure the number Xenia thought of?
Incorrect response:
Ксения и Сергей играют в следующую игру. Ксения загадывает положительное целое число $N$, не превышающее 5000. Затем она фиксирует 20 различных положительных целых чисел $a_{1}, a_{2}, \ldots, a_{20}$, таких, что для каждого $k=1,2, \ldots, 20$ числа $N$ и $a_{k}$ конгруэнтны по модулю $k$. За один ход Сергей сообщает Ксении множество $S$ положительных целых чисел, не превышающих 20, а она в ответ сообщает ему множество $\left\{a_{k}: k \in S\right\}$, не уточняя, какому индексу соответствует какое число. Сколько ходов нужно Сергею, чтобы точно определить число, которое загадала Ксения?
Thanks so much for the feedback, this is very valuable! I have shared it with the team that developed this model, and we will look into it to avoid this sort of issues in future model releases. If you come across more unexpected behavior, please report it to us!
