Instructions to use Skskskd/teste-modelo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skskskd/teste-modelo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Skskskd/teste-modelo")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Skskskd/teste-modelo") model = AutoModelForCausalLM.from_pretrained("Skskskd/teste-modelo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Skskskd/teste-modelo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Skskskd/teste-modelo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Skskskd/teste-modelo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Skskskd/teste-modelo
- SGLang
How to use Skskskd/teste-modelo 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 "Skskskd/teste-modelo" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Skskskd/teste-modelo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "Skskskd/teste-modelo" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Skskskd/teste-modelo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Skskskd/teste-modelo with Docker Model Runner:
docker model run hf.co/Skskskd/teste-modelo
Upload model
Browse files- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"summary_type": "cls_index",
|
| 29 |
"summary_use_proj": true,
|
| 30 |
"tie_word_embeddings": true,
|
| 31 |
-
"transformers_version": "5.
|
| 32 |
-
"use_cache":
|
| 33 |
"vocab_size": 50257
|
| 34 |
}
|
|
|
|
| 28 |
"summary_type": "cls_index",
|
| 29 |
"summary_use_proj": true,
|
| 30 |
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.16.1",
|
| 32 |
+
"use_cache": true,
|
| 33 |
"vocab_size": 50257
|
| 34 |
}
|
generation_config.json
CHANGED
|
@@ -7,6 +7,6 @@
|
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
"pad_token_id": 50256,
|
| 10 |
-
"transformers_version": "5.
|
| 11 |
"use_cache": true
|
| 12 |
}
|
|
|
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
"pad_token_id": 50256,
|
| 10 |
+
"transformers_version": "5.16.1",
|
| 11 |
"use_cache": true
|
| 12 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 121365368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91ba569cd7f2858d74469073b8870e78e6b703f9f62cb9df7afafef5bbbaefb1
|
| 3 |
size 121365368
|