CRS-4B by Charcot AI

CRS-4B

CRS-4B is a 4B clinical tool-use model. It is fine-tuned from Qwen3.5-4B on public synthetic episodes from Charcot Gym, an EHR environment where agents read clinical context, call tools, and write structured FHIR records.

Property Value
Base model Qwen/Qwen3.5-4B
Parameters 4.66B (BF16)
Training data Public synthetic tasks from charcot-ai/gym
Evaluation 99 held-out private Charcot Gym tasks, 3 attempts per task
Task families Document → FHIR, Clinical coding, Claims
Intended use Research and evaluation of clinical tool use

Quickstart

Install a recent transformers (the weights were saved with 5.17), then ask the model to act through a tool:

pip install "transformers>=5.17" torch accelerate
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "charcot-ai/crs-4b"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="auto", device_map="auto")

tools = [{
    "type": "function",
    "function": {
        "name": "fhir_create",
        "description": "Create a FHIR R5 resource in the patient's chart.",
        "parameters": {
            "type": "object",
            "properties": {"resource": {"type": "object", "description": "FHIR R5 resource JSON"}},
            "required": ["resource"],
        },
    },
}]
messages = [{
    "role": "user",
    "content": "Patient/avery-1. New lab report, 2025-07-06: ALT 49 U/L. Save this result to the chart.",
}]

inputs = processor.apply_chat_template(
    messages, tools=tools, add_generation_prompt=True,
    tokenize=True, return_dict=True, return_tensors="pt",
).to(model.device)
output = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Outputs

The chat template opens a <think> block, so the decoded text is the model's reasoning, a closing </think>, and then zero or more tool calls in the Qwen3.5 format:

<tool_call>
<function=fhir_create>
<parameter=resource>
{"resourceType": "...", ...}
</parameter>
</function>
</tool_call>
Part What to do with it
Text before </think> Reasoning; drop it or log it
<function=NAME> Name of the tool to call
<parameter=KEY> One argument; the value is JSON when the schema type is an object

Run the tool, append the result as a {"role": "tool", "content": ...} message, and generate again until the model answers without a tool call.

To score the model on real tasks, serve it behind an OpenAI-compatible endpoint and run charcot-gym eval as described in the Charcot Gym README.

Results

Model Mean task score
Qwen3.5-4B (base) 0.16
CRS-4B (fine-tuned) 0.86
Frontier models on the same tasks 0.76–0.89

99 private tasks, 3 attempts per task, November 2026. The private tasks were never seen in training. A deterministic offline verifier checks the final record and task constraints; no LLM judge is used. These scores describe performance on the evaluated tasks; they do not establish a general ranking outside this evaluation.

Training and evaluation

Stage Detail
Training Supervised fine-tuning on public synthetic Gym episodes only
Evaluation Held-out private split, repeated attempts per task
Integrity checks Patient identity and preservation of existing resources
Private reporting Aggregate scores only; private task contents, per-task outputs, and trajectories are not returned to submitters

See the evaluation methodology for scoring and the submission policy.

Files

Path Contents
model.safetensors-* Merged weights; load with the Quickstart above
adapter/ The LoRA adapter (rank 32) for Qwen/Qwen3.5-4B
chat_template.jinja Chat template with tool-call formatting

Limitations

  • The reported result measures synthetic task completion, not performance in patient care. Do not use the model for clinical decisions.
  • Training and evaluation data are synthetic and in English.
  • Scores cover the three task families above; other Charcot Gym families and other clinical tasks were not reported here.

Citation

@misc{charcot2026crs4b,
  title        = {CRS-4B: A clinical tool-use model trained in a synthetic EHR},
  author       = {{Charcot AI}},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/charcot-ai/crs-4b}}
}

Charcot AI

Longitudinal data and evaluation infrastructure for healthcare AI agents. charcot.ai · Charcot Gym · Public tasks

Downloads last month
77
Safetensors
Model size
5B params
Tensor type
BF16
·
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for charcot-ai/crs-4b

Finetuned
Qwen/Qwen3.5-4B
Finetuned
(1,474)
this model

Dataset used to train charcot-ai/crs-4b