Instructions to use RemDev-AI/medical-triage-agent-ai-poc-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use RemDev-AI/medical-triage-agent-ai-poc-models with PEFT:
```
Task type is invalid.
```

How to use RemDev-AI/medical-triage-agent-ai-poc-models with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RemDev-AI/medical-triage-agent-ai-poc-models")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RemDev-AI/medical-triage-agent-ai-poc-models", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RemDev-AI/medical-triage-agent-ai-poc-models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RemDev-AI/medical-triage-agent-ai-poc-models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RemDev-AI/medical-triage-agent-ai-poc-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RemDev-AI/medical-triage-agent-ai-poc-models

SGLang

How to use RemDev-AI/medical-triage-agent-ai-poc-models 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 "RemDev-AI/medical-triage-agent-ai-poc-models" \
    --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": "RemDev-AI/medical-triage-agent-ai-poc-models",
		"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 "RemDev-AI/medical-triage-agent-ai-poc-models" \
        --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": "RemDev-AI/medical-triage-agent-ai-poc-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RemDev-AI/medical-triage-agent-ai-poc-models with Docker Model Runner:
```
docker model run hf.co/RemDev-AI/medical-triage-agent-ai-poc-models
```

RemDev-AI commited on Jul 27

Commit

b1ea393

verified ·

1 Parent(s): 20279ac

Clinical evaluation report (markdown_report) — qwen3-1.7b-dpo

Browse files

Files changed (1) hide show

dpo/evaluation_reports/qwen3-1.7b-dpo/evaluation_report.md +53 -0

dpo/evaluation_reports/qwen3-1.7b-dpo/evaluation_report.md ADDED Viewed

	@@ -0,0 +1,53 @@

+# Clinical Evaluation Report
+**Model:** qwen3-1.7b-dpo
+**Timestamp:** 2026-07-27T21:24:44.312549Z
+**Status:** FAIL
+---
+## Clinical Metrics
+- **priority_accuracy**: 0.2000
+- **clinical_accuracy**: 0.2000
+- **recommendation_accuracy**: 0.2000
+- **safety_accuracy**: 1.0000
+---
+## Safety Evaluation
+- **hallucination_rate**: 0.0000
+- **unsafe_claim_rate**: 0.0000
+- **dangerous_rate**: 0.0000
+- **safety_score**: 1.0000
+- **thresholds_passed**: 1.0000
+---
+## Thresholds
+- **min_priority_accuracy**: 0.8500
+- **min_safety_score**: 0.9500
+- **max_hallucination_rate**: 0.0500
+- **max_dangerous_rate**: 0.0200
+- **max_unsafe_claim_rate**: 0.0300
+---
+## Metadata
+- **full_dataset_size**: 40
+- **qcm_subset_size**: 15
+- **full_dataset_safety_scan**: {'hallucination_rate': 0.0, 'unsafe_claim_rate': 0.0, 'dangerous_rate': 0.0, 'safety_score': 1.0, 'thresholds_passed': True}
+- **stage_timings_seconds**: {'chargement_modele': 280.3, 'telechargement_et_chargement_dataset': 0.1, 'generation_reponses_modele': 0.7, 'scan_securite_qcm_subset': 0.0, 'scan_securite_dataset_complet': 0.1}
+- **model_name**: qwen3-1.7b-dpo
+- **model_revision**: main
+- **dataset_split**: clinical_eval
+- **evaluation_timestamp**: 2026-07-27T21:24:44.277848Z
+---
+## Summary
+Model does not satisfy clinical evaluation requirements.