Text Generation
Transformers
Safetensors
English
Chinese
llama
text2sql
conversational
text-generation-inference
Instructions to use xbrain/AutoSQL-nl2sql-1.0-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xbrain/AutoSQL-nl2sql-1.0-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xbrain/AutoSQL-nl2sql-1.0-8b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("xbrain/AutoSQL-nl2sql-1.0-8b") model = AutoModelForCausalLM.from_pretrained("xbrain/AutoSQL-nl2sql-1.0-8b", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xbrain/AutoSQL-nl2sql-1.0-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xbrain/AutoSQL-nl2sql-1.0-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xbrain/AutoSQL-nl2sql-1.0-8b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/xbrain/AutoSQL-nl2sql-1.0-8b
- SGLang
How to use xbrain/AutoSQL-nl2sql-1.0-8b 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 "xbrain/AutoSQL-nl2sql-1.0-8b" \ --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": "xbrain/AutoSQL-nl2sql-1.0-8b", "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 "xbrain/AutoSQL-nl2sql-1.0-8b" \ --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": "xbrain/AutoSQL-nl2sql-1.0-8b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use xbrain/AutoSQL-nl2sql-1.0-8b with Docker Model Runner:
docker model run hf.co/xbrain/AutoSQL-nl2sql-1.0-8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,6 +65,27 @@ outputs = pipe_msg(
|
|
| 65 |
print(outputs[0]["generated_text"][-1])
|
| 66 |
```
|
| 67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
## 3. Ethical Considerations
|
| 70 |
|
|
|
|
| 65 |
print(outputs[0]["generated_text"][-1])
|
| 66 |
```
|
| 67 |
|
| 68 |
+
Here are some exciting examples:
|
| 69 |
+
**Example 1:**
|
| 70 |
+
- model input:
|
| 71 |
+
{"role": "system",
|
| 72 |
+
"content": "I want you to act as a SQL terminal in front of an example database, you need only to return the sql command to me.Below is an instruction that describes a task, Write a response that appropriately completes the request.\n\"\n##Instruction:\ndog_kennels contains tables such as Breeds, Charges, Sizes, Treatment_Types, Owners, Dogs, Professionals, Treatments. Table Breeds has columns such as breed_code, breed_name. breed_code is the primary key.\nTable Charges has columns such as charge_id, charge_type, charge_amount. charge_id is the primary key.\nTable Sizes has columns such as size_code, size_description. size_code is the primary key.\nTable Treatment_Types has columns such as treatment_type_code, treatment_type_description. treatment_type_code is the primary key.\nTable Owners has columns such as owner_id, first_name, last_name, street, city, state, zip_code, email_address, home_phone, cell_number. owner_id is the primary key.\nTable Dogs has columns such as dog_id, owner_id, abandoned_yn, breed_code, size_code, name, age, date_of_birth, gender, weight, date_arrived, date_adopted, date_departed. dog_id is the primary key.\nTable Professionals has columns such as professional_id, role_code, first_name, street, city, state, zip_code, last_name, email_address, home_phone, cell_number. professional_id is the primary key.\nTable Treatments has columns such as treatment_id, dog_id, professional_id, treatment_type_code, date_of_treatment, cost_of_treatment. treatment_id is the primary key.\nThe owner_id of Dogs is the foreign key of owner_id of Owners.\nThe owner_id of Dogs is the foreign key of owner_id of Owners.\nThe size_code of Dogs is the foreign key of size_code of Sizes.\nThe breed_code of Dogs is the foreign key of breed_code of Breeds.\nThe dog_id of Treatments is the foreign key of dog_id of Dogs.\nThe professional_id of Treatments is the foreign key of professional_id of Professionals.\nThe treatment_type_code of Treatments is the foreign key of treatment_type_code of Treatment_Types.\n\n"},
|
| 73 |
+
{"role": "user",
|
| 74 |
+
"content": "###Input:\n列出每种治疗的费用和相应的治疗类型描述。\n\n###Response:"},
|
| 75 |
+
|
| 76 |
+
- model output:
|
| 77 |
+
{'role': 'assistant', 'content': 'SELECT T1.cost_of_treatment, T2.treatment_type_description FROM Treatments AS T1 JOIN treatment_types AS T2 ON T1.treatment_type_code = T2.treatment_type_code'}
|
| 78 |
+
|
| 79 |
+
**Example 2:**
|
| 80 |
+
- model input:
|
| 81 |
+
{"role": "system",
|
| 82 |
+
"content": "I want you to act as a SQL terminal in front of an example database, you need only to return the sql command to me.Below is an instruction that describes a task, Write a response that appropriately completes the request.\n\"\n##Instruction:\n database contains tables such as medication, vitalperiodic, diagnosis, cost, lab, microlab, intakeoutput, treatment, patient, allergy. Table medication has columns such as medicationid, patientunitstayid, drugname, dosage, routeadmin, drugstarttime, drugstoptime. Table vitalperiodic has columns such as vitalperiodicid, patientunitstayid, temperature, sao2, heartrate, respiration, systemicsystolic, systemicdiastolic, systemicmean, observationtime. Table diagnosis has columns such as diagnosisid, patientunitstayid, diagnosisname, diagnosistime, icd9code. Table cost has columns such as costid, uniquepid, patienthealthsystemstayid, eventtype, eventid, chargetime, cost. Table lab has columns such as labid, patientunitstayid, labname, labresult, labresulttime. Table microlab has columns such as microlabid, patientunitstayid, culturesite, organism, culturetakentime. Table intakeoutput has columns such as intakeoutputid, patientunitstayid, cellpath, celllabel, cellvaluenumeric, intakeoutputtime. Table treatment has columns such as treatmentid, patientunitstayid, treatmentname, treatmenttime. Table patient has columns such as uniquepid, patienthealthsystemstayid, patientunitstayid, gender, age, ethnicity, hospitalid, wardid, admissionheight, admissionweight, dischargeweight, hospitaladmittime, hospitaladmitsource, unitadmittime, unitdischargetime, hospitaldischargetime, hospitaldischargestatus. Table allergy has columns such as allergyid, patientunitstayid, drugname, allergyname, allergytime. \n"},
|
| 83 |
+
{"role": "user",
|
| 84 |
+
"content": "###Input:\n did the first urine, catheter specimen microbiology test of patient 031-15666 in the last month show any organism?\n\n###Response:"},
|
| 85 |
+
|
| 86 |
+
- model output:
|
| 87 |
+
{'role': 'assistant', 'content': "SELECT COUNT(*) > 0 FROM microlab WHERE microlab.patientunitstayid IN (SELECT patient.patientunitstayid FROM patient WHERE patient.patienthealthsystemstayid IN (SELECT patient.patienthealthsystemstayid FROM patient WHERE patient.uniquepid = '031-15666')) AND microlab.culturesite = 'urine, catheter specimen' AND DATETIME(microlab.culturetakentime,'start of month') = DATETIME(CURRENT_TIME(),'start of month', '-1 month') ORDER BY microlab.culturetakentime LIMIT 1"}
|
| 88 |
+
|
| 89 |
|
| 90 |
## 3. Ethical Considerations
|
| 91 |
|