Publish stravoris/medmcq-anatomy-qwen3-1.7b

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,111 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-1.7B
+tags:
+  - medical
+  - mcq
+  - question-answering
+  - anatomy
+  - qwen3
+  - medmcq
+  - stravoris
+pipeline_tag: text-generation
+language:
+  - en
+---
+
+# MedMCQ — Anatomy Answer Generator (Qwen3-1.7B)
+
+A small fine-tuned Qwen3 model that **answers Anatomy medical multiple-choice questions (MCQs)**. Given an Anatomy topic, an MCQ stem, and four lettered options, it returns the correct option and a brief clinical explanation.
+
+This is a **per-subject answer generator** — the third hop in the [MedMCQ three-hop pipeline](#the-medmcq-pipeline). It is reached only after the [subject classifier](https://huggingface.co/stravoris/medmcq-subject-classifier-qwen3-0.6b) has routed the MCQ to Anatomy and the [Anatomy topic classifier](https://huggingface.co/stravoris/medmcq-anatomy-classifier-qwen3-0.6b) has tagged it with a topic.
+
+## The MedMCQ pipeline
+
+The MedMCQ project explores small, specialized models for medical MCQs. Instead of using one large model for everything, it splits the task across three hops:
+
+1. **Subject routing** — the [subject classifier](https://huggingface.co/stravoris/medmcq-subject-classifier-qwen3-0.6b) picks the medical subject.
+2. **Topic classification** — the [Anatomy topic classifier](https://huggingface.co/stravoris/medmcq-anatomy-classifier-qwen3-0.6b) picks the topic within Anatomy.
+3. **Answer generation** — *this model.* Given the topic and the MCQ, return the correct option and an explanation.
+
+Each hop is a separate, narrow model. They are all published under the [MedMCQ Medical Models](https://huggingface.co/collections/stravoris/medmcq-medical-models) collection.
+
+## Quick start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo = "stravoris/medmcq-anatomy-qwen3-1.7b"
+tokenizer = AutoTokenizer.from_pretrained(repo)
+model = AutoModelForCausalLM.from_pretrained(repo)
+
+prompt = """Answer the following medical question. Provide the correct option and a brief explanation.
+
+Topic: <an Anatomy topic>
+
+Question: <the MCQ stem>
+
+Options:
+A) <option A>
+B) <option B>
+C) <option C>
+D) <option D>"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+## Prompt format
+
+The model expects prompts in this exact form:
+
+```
+Answer the following medical question. Provide the correct option and a brief explanation.
+
+Topic: <topic name>
+
+Question: <question stem>
+
+Options:
+A) <option A>
+B) <option B>
+C) <option C>
+D) <option D>
+```
+
+The model completes the prompt with the correct option and a short clinical explanation, in the form:
+
+```
+<letter>) <correct option text>
+
+<brief explanation>
+```
+
+## What this model is not
+
+This is a **sample model for demonstration**. It is not a production-grade medical AI system:
+
+- It has not been formally evaluated against board-level benchmarks.
+- It should not be used to make clinical decisions or provide medical advice.
+- Returned answers and explanations may contain factual errors or outdated information. A clinician should review every output before any educational use.
+- It is narrow: it only answers Anatomy MCQs and is brittle outside that domain or on prompts that deviate from the format above.
+- It was trained on a curated educational dataset and inherits any biases or gaps in that data.
+
+The MedMCQ project exists to explore small-model pipeline architectures for medical reasoning, not to ship a medical product.
+
+## Training data
+
+Trained on the Anatomy slice of the [`stravoris/medmcq-anatomy`](https://huggingface.co/datasets/stravoris/medmcq-anatomy) dataset — educational Anatomy MCQs with topic labels, stems, lettered options, the correct option, and a worked explanation.
+
+## Base model
+
+Fine-tuned from [`Qwen/Qwen3-1.7B`](https://huggingface.co/Qwen/Qwen3-1.7B). The base model's license and usage terms also apply.
+
+## License
+
+Apache 2.0. See [LICENSE](https://www.apache.org/licenses/LICENSE-2.0).
+
+## Collection
+
+Part of the [MedMCQ Medical Models](https://huggingface.co/collections/stravoris/medmcq-medical-models) collection — all 31 models that make up the MedMCQ three-hop pipeline.

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 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "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": "5.7.0",
+  "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": "5.7.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb3ab844d4c51803ee98a113cb16a806fa99d88fe83a9b21fcb647e0266b260
+size 3441185296

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}