Publish PertMind model

.gitattributes

@@ -1,35 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,186 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and
+distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the
+copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other
+entities that control, are controlled by, or are under common control with
+that entity. For the purposes of this definition, "control" means (i) the
+power, direct or indirect, to cause the direction or management of such
+entity, whether by contract or otherwise, or (ii) ownership of fifty percent
+(50%) or more of the outstanding shares, or (iii) beneficial ownership of
+such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising
+permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation source, and
+configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or
+translation of a Source form, including but not limited to compiled object
+code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form,
+made available under the License, as indicated by a copyright notice that is
+included in or attached to the work (an example is provided in the Appendix
+below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form,
+that is based on (or derived from) the Work and for which the editorial
+revisions, annotations, elaborations, or other modifications represent, as a
+whole, an original work of authorship. For the purposes of this License,
+Derivative Works shall not include works that remain separable from, or
+merely link (or bind by name) to the interfaces of, the Work and Derivative
+Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original
+version of the Work and any modifications or additions to that Work or
+Derivative Works thereof, that is intentionally submitted to Licensor for
+inclusion in the Work by the copyright owner or by an individual or Legal
+Entity authorized to submit on behalf of the copyright owner. For the
+purposes of this definition, "submitted" means any form of electronic,
+verbal, or written communication sent to the Licensor or its representatives,
+including but not limited to communication on electronic mailing lists,
+source code control systems, and issue tracking systems that are managed by,
+or on behalf of, the Licensor for the purpose of discussing and improving the
+Work, but excluding communication that is conspicuously marked or otherwise
+designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and subsequently
+incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable copyright license to
+reproduce, prepare Derivative Works of, publicly display, publicly perform,
+sublicense, and distribute the Work and such Derivative Works in Source or
+Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this
+section) patent license to make, have made, use, offer to sell, sell, import,
+and otherwise transfer the Work, where such license applies only to those
+patent claims licensable by such Contributor that are necessarily infringed by
+their Contribution(s) alone or by combination of their Contribution(s) with
+the Work to which such Contribution(s) was submitted. If You institute patent
+litigation against any entity (including a cross-claim or counterclaim in a
+lawsuit) alleging that the Work or a Contribution incorporated within the Work
+constitutes direct or contributory patent infringement, then any patent
+licenses granted to You under this License for that Work shall terminate as of
+the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or
+Derivative Works thereof in any medium, with or without modifications, and in
+Source or Object form, provided that You meet the following conditions:
+
+(a) You must give any other recipients of the Work or Derivative Works a copy
+of this License; and
+
+(b) You must cause any modified files to carry prominent notices stating that
+You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works that You
+distribute, all copyright, patent, trademark, and attribution notices from
+the Source form of the Work, excluding those notices that do not pertain to
+any part of the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its distribution,
+then any Derivative Works that You distribute must include a readable copy of
+the attribution notices contained within such NOTICE file, excluding those
+notices that do not pertain to any part of the Derivative Works, in at least
+one of the following places: within a NOTICE text file distributed as part of
+the Derivative Works; within the Source form or documentation, if provided
+along with the Derivative Works; or, within a display generated by the
+Derivative Works, if and wherever such third-party notices normally appear.
+The contents of the NOTICE file are for informational purposes only and do not
+modify the License. You may add Your own attribution notices within
+Derivative Works that You distribute, alongside or as an addendum to the
+NOTICE text from the Work, provided that such additional attribution notices
+cannot be construed as modifying the License.
+
+You may add Your own copyright statement to Your modifications and may provide
+additional or different license terms and conditions for use, reproduction, or
+distribution of Your modifications, or for any such Derivative Works as a
+whole, provided Your use, reproduction, and distribution of the Work otherwise
+complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any
+Contribution intentionally submitted for inclusion in the Work by You to the
+Licensor shall be under the terms and conditions of this License, without any
+additional terms or conditions. Notwithstanding the above, nothing herein
+shall supersede or modify the terms of any separate license agreement you may
+have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names,
+trademarks, service marks, or product names of the Licensor, except as
+required for reasonable and customary use in describing the origin of the Work
+and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in
+writing, Licensor provides the Work (and each Contributor provides its
+Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied, including, without limitation, any warranties
+or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Work and assume any risks
+associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in
+tort, contract, or otherwise, unless required by applicable law (such as
+deliberate and grossly negligent acts) or agreed to in writing, shall any
+Contributor be liable to You for damages, including any direct, indirect,
+special, incidental, or consequential damages of any character arising as a
+result of this License or out of the use or inability to use the Work
+(including but not limited to damages for loss of goodwill, work stoppage,
+computer failure or malfunction, or any and all other commercial damages or
+losses), even if such Contributor has been advised of the possibility of such
+damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work
+or Derivative Works thereof, You may choose to offer, and charge a fee for,
+acceptance of support, warranty, indemnity, or other liability obligations
+and/or rights consistent with this License. However, in accepting such
+obligations, You may act only on Your own behalf and on Your sole
+responsibility, not on behalf of any other Contributor, and only if You agree
+to indemnify, defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason of your
+accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+To apply the Apache License to your work, attach the following boilerplate
+notice, with the fields enclosed by brackets "[]" replaced with your own
+identifying information. (Don't include the brackets!) The text should be
+enclosed in the appropriate comment syntax for the file format. We also
+recommend that a file or class name and description of purpose be included on
+the same "printed page" as the copyright notice for easier identification
+within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

README.md

@@ -0,0 +1,144 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-4B-Base
+tags:
+  - biology
+  - biomedical
+  - perturbation-response
+  - reinforcement-learning
+  - qwen3
+  - transformers
+  - vllm
+---
+
+# PertMind
+
+PertMind is a biological language model built around a central discovery: public cellular perturbation atlases can be reorganized into reinforcement-learning environments, where measured gene responses act as computable reward signals for biological reasoning. Instead of relying only on manually curated reasoning traces, PertMind combines trusted-trajectory supervised initialization with perturbation-derived reinforcement learning for perturbation-centered inference and biological profile generation.
+
+PertMind is initialized from [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base). The project repository is [shapsider/PertMind](https://github.com/shapsider/PertMind).
+
+![Figure 1](assets/Figure1.png)
+
+*Figure 1. Schematic scope of the capabilities enabled by PertMind. Reasoning-based applications use natural-language inference for perturbation-response prediction, perturbation prioritization, mechanism reasoning, and proposal planning. Embedding-based applications encode PertMind-generated biological profiles into reusable molecular, cellular, and donor representations for reference mapping, cellular perturbation-response prediction, and donor-level tumor-state reference mapping. The figure summarizes the intended capability space, not benchmark performance. Within this space, the quantitatively evaluated subset in the manuscript covers forward perturbation-response prediction, reverse perturbation-condition inference, phenotypic-screen hit prioritization, biological-process naming, and molecular-, cellular-, and donor-level reference mapping.*
+
+## Model Summary
+
+PertMind starts from the Qwen3-4B base model family and treats perturbation-response prediction as a training interface for biological reasoning. Each query is centered on a `(cell line, perturbation, target gene)` triplet. The model receives retrieved biological context, but the query-specific endpoint remains hidden from the prompt. Training then rewards responses that align with experimentally observed perturbation outcomes.
+
+The released package preserves the model configuration, tokenizer assets, and three runnable inference entry points included in this repository:
+
+- `inference_vllm.py`
+- `inference_transformers.py`
+- `tui_chat.py`
+
+## Perturbation-Derived RL
+
+PertMind operationalizes perturbation-derived reinforcement learning in three stages:
+
+1. Gene-centered queries are assembled from the Tahoe-100M perturbation atlas and paired with experimentally derived `Up`, `Down`, or `No` response labels.
+2. A small trusted set of model-generated trajectories provides structured supervised initialization, giving the policy an evidence-grounded starting point before reinforcement learning.
+3. Group Relative Policy Optimization then optimizes a composite reward with three parts: a gene-level endpoint reward, a pathway-direction reward derived from transcriptional response summaries, and a format reward that keeps outputs parseable.
+
+This setup is meant to test whether reinforcement on experimental endpoints can concentrate reusable biological strategies that are already accessible to a pretrained language model.
+
+## Operational Emergence
+
+In the PertMind manuscript, *emergence* is used in an operational sense: a capability appears on a target task that was absent from post-training. PertMind is post-trained only on forward perturbation-response prediction, while the manuscript evaluates transfer to other biological tasks such as reverse perturbation-condition inference, phenotypic-screen prioritization, biological-process interpretation, and multiscale representation construction.
+
+This framing is intentionally bounded. Transfer outside the post-training objective supports the hypothesis that PertMind learns reusable biological strategies, but it does not prove that every free-text reasoning trace is mechanistically faithful.
+
+## Intended Uses
+
+Evidence-supported uses described in the manuscript include:
+
+- forward perturbation-response reasoning in held-out biological contexts;
+- reverse perturbation-condition inference and related transfer settings absent from post-training;
+- biological-process interpretation and screen-oriented biological briefing;
+- generation of PertMind-derived biological profiles for downstream molecular, cellular, and donor-level representations.
+
+Broader intended capability scope illustrated in Figure 1 includes mechanism reasoning and proposal planning. Figure 1 should be read as a capability overview, not as a benchmark summary.
+
+## Out-Of-Scope Uses
+
+PertMind is not intended for:
+
+- clinical diagnosis, treatment selection, or other medical decision-making;
+- replacing wet-lab validation or expert biological review;
+- claims of faithful causal mechanism recovery from endpoint accuracy alone;
+- unrestricted deployment to perturbation modalities, tissues, doses, or disease states that were not studied in the released work.
+
+## Quick Start
+
+Create a clean environment and install dependencies:
+
+```bash
+conda create -n pertmind python=3.11 -y
+conda activate pertmind
+pip install -r requirements.txt
+```
+
+If multiple Python environments are present, verify that the active interpreter is the one from `pertmind`:
+
+```bash
+which python
+python -c "import sys; print(sys.executable)"
+```
+
+Run a single prompt with vLLM:
+
+```bash
+python inference_vllm.py \
+  --model . \
+  --prompt "In HCT116, predict how LMBR1 changes expression of SLC26A6."
+```
+
+Run a single prompt with Transformers:
+
+```bash
+python inference_transformers.py \
+  --model . \
+  --prompt "In HCT116, predict how LMBR1 changes expression of SLC26A6."
+```
+
+Start the terminal chat interface:
+
+```bash
+python tui_chat.py --model . --backend vllm
+```
+
+Useful TUI commands:
+
+```text
+/reset  clear conversation history
+/exit   quit
+```
+
+## Tested Setup
+
+The release content was prepared against the included runtime files and dependency pins:
+
+- Python 3.11
+- PyTorch 2.10.0
+- Transformers 5.14.0
+- Accelerate 1.14.0
+- Safetensors 0.8.0
+- vLLM 0.19.1
+
+The model package is approximately 7.5 GB in `bfloat16`. A GPU with at least 16 GB VRAM is recommended for basic inference. Larger context lengths and vLLM serving may require more VRAM, and the first vLLM run may spend extra time compiling and caching CUDA graphs.
+
+## Limitations And Responsible Use
+
+- Endpoint correctness does not by itself establish a faithful causal mechanism.
+- Free-text trajectories are auditable, but the reward does not verify every intermediate reasoning step.
+- Pathway supervision is a transcriptional proxy and does not directly measure protein activity, metabolic flux, spatial signaling, or causal pathway activation.
+- The evaluated datasets, interventions, and downstream tasks cover only part of biological diversity, so generalization outside the studied settings remains unresolved.
+- Retrieval resources and trusted trajectories may propagate omissions, annotation errors, and historical biases from their sources.
+- PertMind-derived embeddings still depend on task-specific projections, aggregation, and downstream supervision.
+
+PertMind is released for research use, hypothesis generation, and method development.
+
+## License
+
+This repository is released under the [Apache-2.0 License](LICENSE).

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.12.0"
+}

inference_transformers.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+"""Run PertMind with Hugging Face Transformers."""
+
+from __future__ import annotations
+
+import argparse
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+DEFAULT_SYSTEM_PROMPT = (
+    "You are PertMind, a biomedical assistant. For biomedical prediction, "
+    "screen-ranking, or gene-set interpretation tasks, answer first and then "
+    "provide a concise explanation. Use this style when applicable:\n"
+    "Final Answer: <answer>\nExplanation: <brief explanation>"
+)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--model", default=".", help="Path or Hugging Face model id.")
+    parser.add_argument("--prompt", required=True, help="User prompt.")
+    parser.add_argument("--system-prompt", default=DEFAULT_SYSTEM_PROMPT)
+    parser.add_argument("--max-new-tokens", type=int, default=768)
+    parser.add_argument("--temperature", type=float, default=0.0)
+    parser.add_argument("--top-p", type=float, default=0.95)
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = parse_args()
+    tokenizer = AutoTokenizer.from_pretrained(args.model, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        args.model,
+        torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
+        device_map="auto",
+        trust_remote_code=True,
+    )
+    messages = [
+        {"role": "system", "content": args.system_prompt},
+        {"role": "user", "content": args.prompt},
+    ]
+    try:
+        text = tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+            enable_thinking=False,
+        )
+    except TypeError:
+        text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = tokenizer(text, return_tensors="pt").to(model.device)
+    do_sample = args.temperature > 0
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=args.max_new_tokens,
+        do_sample=do_sample,
+        temperature=args.temperature if do_sample else None,
+        top_p=args.top_p if do_sample else None,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    generated = outputs[0, inputs["input_ids"].shape[-1] :]
+    print(tokenizer.decode(generated, skip_special_tokens=True).strip())
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

inference_vllm.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""Run PertMind with vLLM."""
+
+from __future__ import annotations
+
+import argparse
+
+from vllm import LLM, SamplingParams
+
+
+DEFAULT_SYSTEM_PROMPT = (
+    "You are PertMind, a biomedical assistant. For biomedical prediction, "
+    "screen-ranking, or gene-set interpretation tasks, answer first and then "
+    "provide a concise explanation. Use this style when applicable:\n"
+    "Final Answer: <answer>\nExplanation: <brief explanation>"
+)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--model", default=".", help="Path or Hugging Face model id.")
+    parser.add_argument("--prompt", required=True, help="User prompt.")
+    parser.add_argument("--system-prompt", default=DEFAULT_SYSTEM_PROMPT)
+    parser.add_argument("--max-tokens", type=int, default=768)
+    parser.add_argument("--temperature", type=float, default=0.0)
+    parser.add_argument("--top-p", type=float, default=0.95)
+    parser.add_argument("--max-model-len", type=int, default=12288)
+    parser.add_argument("--gpu-memory-utilization", type=float, default=0.85)
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = parse_args()
+    llm = LLM(
+        model=args.model,
+        trust_remote_code=True,
+        dtype="bfloat16",
+        max_model_len=args.max_model_len,
+        gpu_memory_utilization=args.gpu_memory_utilization,
+    )
+    tokenizer = llm.get_tokenizer()
+    messages = [
+        {"role": "system", "content": args.system_prompt},
+        {"role": "user", "content": args.prompt},
+    ]
+    try:
+        text = tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+            enable_thinking=False,
+        )
+    except TypeError:
+        text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    params = SamplingParams(
+        temperature=args.temperature,
+        top_p=args.top_p,
+        max_tokens=args.max_tokens,
+    )
+    output = llm.generate([text], params)[0].outputs[0].text.strip()
+    print(output)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523a2b0dc10f350407064b804815a5fe22089fd1e54fae99072c620841081ca0
+size 8044982080

requirements.txt

@@ -0,0 +1,5 @@
+torch==2.10.0
+transformers==5.14.0
+accelerate==1.14.0
+safetensors==0.8.0
+vllm==0.19.1

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

tui_chat.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+"""A small terminal chat UI for PertMind."""
+
+from __future__ import annotations
+
+import argparse
+from dataclasses import dataclass
+
+
+DEFAULT_SYSTEM_PROMPT = (
+    "You are PertMind, a biomedical assistant. For biomedical prediction, "
+    "screen-ranking, or gene-set interpretation tasks, answer first and then "
+    "provide a concise explanation. Use this style when applicable:\n"
+    "Final Answer: <answer>\nExplanation: <brief explanation>"
+)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--model", default=".", help="Path or Hugging Face model id.")
+    parser.add_argument("--backend", choices=["vllm", "transformers"], default="vllm")
+    parser.add_argument("--system-prompt", default=DEFAULT_SYSTEM_PROMPT)
+    parser.add_argument("--max-new-tokens", type=int, default=768)
+    parser.add_argument("--temperature", type=float, default=0.0)
+    parser.add_argument("--top-p", type=float, default=0.95)
+    parser.add_argument("--max-model-len", type=int, default=12288)
+    parser.add_argument("--gpu-memory-utilization", type=float, default=0.85)
+    return parser.parse_args()
+
+
+def render_chat(tokenizer, messages: list[dict[str, str]]) -> str:
+    try:
+        return tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+            enable_thinking=False,
+        )
+    except TypeError:
+        return tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+
+@dataclass
+class VllmBackend:
+    model: str
+    max_model_len: int
+    gpu_memory_utilization: float
+
+    def __post_init__(self) -> None:
+        from vllm import LLM
+
+        self.llm = LLM(
+            model=self.model,
+            trust_remote_code=True,
+            dtype="bfloat16",
+            max_model_len=self.max_model_len,
+            gpu_memory_utilization=self.gpu_memory_utilization,
+        )
+        self.tokenizer = self.llm.get_tokenizer()
+
+    def generate(self, messages: list[dict[str, str]], max_new_tokens: int, temperature: float, top_p: float) -> str:
+        from vllm import SamplingParams
+
+        prompt = render_chat(self.tokenizer, messages)
+        params = SamplingParams(temperature=temperature, top_p=top_p, max_tokens=max_new_tokens)
+        return self.llm.generate([prompt], params)[0].outputs[0].text.strip()
+
+
+@dataclass
+class TransformersBackend:
+    model: str
+
+    def __post_init__(self) -> None:
+        import torch
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+
+        self.torch = torch
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model, trust_remote_code=True)
+        self.llm = AutoModelForCausalLM.from_pretrained(
+            self.model,
+            torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
+            device_map="auto",
+            trust_remote_code=True,
+        )
+
+    def generate(self, messages: list[dict[str, str]], max_new_tokens: int, temperature: float, top_p: float) -> str:
+        prompt = render_chat(self.tokenizer, messages)
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.llm.device)
+        do_sample = temperature > 0
+        outputs = self.llm.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            do_sample=do_sample,
+            temperature=temperature if do_sample else None,
+            top_p=top_p if do_sample else None,
+            pad_token_id=self.tokenizer.eos_token_id,
+        )
+        generated = outputs[0, inputs["input_ids"].shape[-1] :]
+        return self.tokenizer.decode(generated, skip_special_tokens=True).strip()
+
+
+def print_panel(title: str, text: str) -> None:
+    line = "=" * min(88, max(20, len(title) + 8))
+    print(f"\n{line}\n{title}\n{line}\n{text}\n")
+
+
+def main() -> int:
+    args = parse_args()
+    if args.backend == "vllm":
+        backend = VllmBackend(args.model, args.max_model_len, args.gpu_memory_utilization)
+    else:
+        backend = TransformersBackend(args.model)
+
+    messages: list[dict[str, str]] = [{"role": "system", "content": args.system_prompt}]
+    print_panel("PertMind TUI", "Type your question and press Enter. Commands: /reset, /exit")
+    while True:
+        try:
+            user_text = input("You> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print()
+            break
+        if not user_text:
+            continue
+        if user_text.lower() in {"/exit", "exit", "quit", "/quit"}:
+            break
+        if user_text.lower() == "/reset":
+            messages = [{"role": "system", "content": args.system_prompt}]
+            print_panel("PertMind", "Conversation reset.")
+            continue
+        messages.append({"role": "user", "content": user_text})
+        answer = backend.generate(messages, args.max_new_tokens, args.temperature, args.top_p)
+        messages.append({"role": "assistant", "content": answer})
+        print_panel("PertMind", answer)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())