Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
8-bit precision
bitsandbytes
Instructions to use shaheerzk/text_to_sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shaheerzk/text_to_sql with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shaheerzk/text_to_sql")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("shaheerzk/text_to_sql") model = AutoModelForCausalLM.from_pretrained("shaheerzk/text_to_sql") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use shaheerzk/text_to_sql with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shaheerzk/text_to_sql" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shaheerzk/text_to_sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/shaheerzk/text_to_sql
- SGLang
How to use shaheerzk/text_to_sql 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 "shaheerzk/text_to_sql" \ --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": "shaheerzk/text_to_sql", "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 "shaheerzk/text_to_sql" \ --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": "shaheerzk/text_to_sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use shaheerzk/text_to_sql with Docker Model Runner:
docker model run hf.co/shaheerzk/text_to_sql
Update generation_config.json
Browse files- generation_config.json +9 -1
generation_config.json
CHANGED
|
@@ -3,5 +3,13 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.35.2"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2",
|
| 7 |
+
|
| 8 |
+
"max_length": 512, // Limits the length of the output text
|
| 9 |
+
"temperature": 0.7, // Controls randomness, higher means more random
|
| 10 |
+
"top_p": 0.9, // Nucleus sampling, considers only top_p highest probability tokens
|
| 11 |
+
"top_k": 50, // Limits the sample space to top_k tokens with highest probabilities
|
| 12 |
+
"do_sample": true, // Enables sampling instead of greedy decoding
|
| 13 |
+
"repetition_penalty": 1.2, // Penalizes repetition
|
| 14 |
+
"num_return_sequences": 1 // Number of output sequences to generate
|
| 15 |
}
|