Text Generation
Transformers
Safetensors
Turkish
gemma2moe
Mixture of Experts
sungur
gemma2
Turkish
Merge
conversational
custom_code
Instructions to use suayptalha/Sungur-3x9B-Cosmos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use suayptalha/Sungur-3x9B-Cosmos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="suayptalha/Sungur-3x9B-Cosmos", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("suayptalha/Sungur-3x9B-Cosmos", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use suayptalha/Sungur-3x9B-Cosmos with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "suayptalha/Sungur-3x9B-Cosmos" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "suayptalha/Sungur-3x9B-Cosmos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/suayptalha/Sungur-3x9B-Cosmos
- SGLang
How to use suayptalha/Sungur-3x9B-Cosmos 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 "suayptalha/Sungur-3x9B-Cosmos" \ --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": "suayptalha/Sungur-3x9B-Cosmos", "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 "suayptalha/Sungur-3x9B-Cosmos" \ --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": "suayptalha/Sungur-3x9B-Cosmos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use suayptalha/Sungur-3x9B-Cosmos with Docker Model Runner:
docker model run hf.co/suayptalha/Sungur-3x9B-Cosmos
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -6,8 +6,8 @@
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"attn_logit_soft_capping": 50.0,
|
| 8 |
"auto_map": {
|
| 9 |
-
"AutoConfig": "suayptalha/turkish-
|
| 10 |
-
"AutoModelForCausalLM": "suayptalha/turkish-
|
| 11 |
},
|
| 12 |
"bos_token_id": 2,
|
| 13 |
"dtype": "bfloat16",
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"num_local_experts": 3,
|
| 28 |
"output_router_logits": false,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
-
"path": "suayptalha/turkish-
|
| 31 |
"query_pre_attn_scalar": 256,
|
| 32 |
"rms_norm_eps": 1e-06,
|
| 33 |
"rope_theta": 10000.0,
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"attn_logit_soft_capping": 50.0,
|
| 8 |
"auto_map": {
|
| 9 |
+
"AutoConfig": "suayptalha/turkish-gemmoe-cosmos-base-router-tuned--configuration_gemma2moe.Gemma2MoeConfig",
|
| 10 |
+
"AutoModelForCausalLM": "suayptalha/turkish-gemmoe-cosmos-base-router-tuned--modeling_gemma2moe.Gemma2MoeForCausalLM"
|
| 11 |
},
|
| 12 |
"bos_token_id": 2,
|
| 13 |
"dtype": "bfloat16",
|
|
|
|
| 27 |
"num_local_experts": 3,
|
| 28 |
"output_router_logits": false,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
+
"path": "suayptalha/turkish-gemmoe-cosmos-base-router-tuned",
|
| 31 |
"query_pre_attn_scalar": 256,
|
| 32 |
"rms_norm_eps": 1e-06,
|
| 33 |
"rope_theta": 10000.0,
|