Text Generation
Transformers
Safetensors
Turkish
English
jamba
mamba
ssm
turkish
conversational
continued-pretraining
sft
Instructions to use serda-dev/Jamba2-3B-Turkish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use serda-dev/Jamba2-3B-Turkish with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="serda-dev/Jamba2-3B-Turkish") 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("serda-dev/Jamba2-3B-Turkish") model = AutoModelForCausalLM.from_pretrained("serda-dev/Jamba2-3B-Turkish", 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 serda-dev/Jamba2-3B-Turkish with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "serda-dev/Jamba2-3B-Turkish" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "serda-dev/Jamba2-3B-Turkish", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/serda-dev/Jamba2-3B-Turkish
- SGLang
How to use serda-dev/Jamba2-3B-Turkish 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 "serda-dev/Jamba2-3B-Turkish" \ --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": "serda-dev/Jamba2-3B-Turkish", "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 "serda-dev/Jamba2-3B-Turkish" \ --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": "serda-dev/Jamba2-3B-Turkish", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use serda-dev/Jamba2-3B-Turkish with Docker Model Runner:
docker model run hf.co/serda-dev/Jamba2-3B-Turkish
Download benchmarks/20261014/comparison.csv from serda-dev/Jamba2-3B-Turkish: direct link, hf CLI and curl.
- Browser
- Download file 2.23 kB
-
https://huggingface.co/serda-dev/Jamba2-3B-Turkish/resolve/main/benchmarks/20261014/comparison.csv
- Command line
-
hf download hf://serda-dev/Jamba2-3B-Turkish/benchmarks/20261014/comparison.csv
-
curl -L -o comparison.csv https://huggingface.co/serda-dev/Jamba2-3B-Turkish/resolve/main/benchmarks/20261014/comparison.csv
2.23 kB
| model,task,correct,n,accuracy,ci95_low,ci95_high,truncated_outputs | |
| jamba_sft,turkish_mmlu,233,900,0.2588888888888889,0.2313385849410743,0.28848878304021797,0 | |
| jamba_sft,belebele_tr,449,900,0.4988888888888889,0.4662965204516904,0.5314907024422324,0 | |
| jamba_sft,gsm8k_tr,45,200,0.225,0.17262283786915622,0.28774246538592035,15 | |
| jamba_sft,gsm8k_tr_cot8,25,200,0.125,0.0861191515921568,0.1780153528465839,58 | |
| jamba_sft,ifeval_tr_subset,38,120,0.31666666666666665,0.2402270792621595,0.4044803534583481,33 | |
| qwen25_3b,turkish_mmlu,367,900,0.4077777777777778,0.3761294528108669,0.4402100473847425,0 | |
| qwen25_3b,belebele_tr,603,900,0.67,0.6386137255634795,0.6999411716663005,0 | |
| qwen25_3b,gsm8k_tr,15,200,0.075,0.045974507057252416,0.12004459797332034,0 | |
| qwen25_3b,gsm8k_tr_cot8,84,200,0.42,0.3537348235017175,0.48928053744521394,3 | |
| qwen25_3b,ifeval_tr_subset,50,120,0.4166666666666667,0.3323820653533033,0.5061213131560184,11 | |
| qwen3_4b_2507,turkish_mmlu,492,900,0.5466666666666666,0.5140128313369314,0.5789238071183023,0 | |
| qwen3_4b_2507,belebele_tr,702,900,0.78,0.7517771913044581,0.8058426394269443,0 | |
| qwen3_4b_2507,gsm8k_tr,138,200,0.69,0.622826945087378,0.75001157266366,10 | |
| qwen3_4b_2507,gsm8k_tr_cot8,140,200,0.7,0.6332080400667355,0.759253557565936,22 | |
| qwen3_4b_2507,ifeval_tr_subset,91,120,0.7583333333333333,0.6744968590361364,0.8261426675849666,8 | |
| jamba_cpt,turkish_mmlu,178,900,0.19777777777777777,0.17306211480827183,0.22506251233878577,0 | |
| jamba_cpt,belebele_tr,259,900,0.2877777777777778,0.25915076813320814,0.3182088046060859,0 | |
| jamba_cpt,gsm8k_tr,19,200,0.095,0.06166261364986359,0.14360265114397636,125 | |
| jamba_cpt,gsm8k_tr_cot8,6,200,0.03,0.013820125830748327,0.06389511973247333,132 | |
| jamba_cpt,ifeval_tr_subset,16,120,0.13333333333333333,0.0837653717755315,0.20564949366548352,97 | |
| jamba_original,turkish_mmlu,205,900,0.22777777777777777,0.20156792872155938,0.25630168028957706,0 | |
| jamba_original,belebele_tr,441,900,0.49,0.457451824253739,0.5226331817915679,0 | |
| jamba_original,gsm8k_tr,38,200,0.19,0.14167093792456506,0.250013585744794,11 | |
| jamba_original,gsm8k_tr_cot8,40,200,0.2,0.15045120743928825,0.26085639611170436,23 | |
| jamba_original,ifeval_tr_subset,56,120,0.4666666666666667,0.3798276424616983,0.5555737089420304,8 | |