Mirror of mlboydaisuke/Qwen3-Embedding-0.6B-CoreAI

.gitattributes

@@ -33,3 +33,5 @@ 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
+qwen3-embedding-0.6b_float16_s512_static.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-Embedding-0.6B
+tags:
+  - coreai
+  - sentence-similarity
+  - feature-extraction
+  - apple-silicon
+  - on-device
+language:
+  - multilingual
+pipeline_tag: sentence-similarity
+---
+
+> **Mirror** of [`mlboydaisuke/Qwen3-Embedding-0.6B-CoreAI`](https://huggingface.co/mlboydaisuke/Qwen3-Embedding-0.6B-CoreAI) — the canonical repo ([CoreAI Model Zoo](https://github.com/john-rocky/coreai-model-zoo)). Updates land there first.
+
+
+# Qwen3-Embedding-0.6B — Core AI export
+
+[Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) as a single static
+Core AI graph for macOS 27 / iOS 27: the full sentence-transformers pipeline (Qwen3-0.6B backbone
+→ **last-token pooling** → **L2 normalize**) runs in-graph, so one call returns a normalized,
+**MRL-truncatable 1024-d** embedding. Multilingual (incl. Japanese), instruction-aware
+on-device semantic search / RAG.
+
+**This is an encoder** — one forward over the (right-padded) input → one pooled vector. No
+autoregressive loop, no KV cache, no LM head. It runs as a plain `.aimodel` via `AIModel.run`
+(like the vision encoders), not the pipelined generate engine.
+
+## Graph contract
+
+| | name | shape | dtype |
+|---|---|---|---|
+| input | `input_ids` | [1, 512] | int32 (right-padded; pad id 151643) |
+| input | `attention_mask` | [1, 512] | int32 (1 = real token, 0 = padding) |
+| output | `embedding` | [1, 1024] | fp16, L2-normalized |
+
+The grid (512) is an export-time choice — a smaller grid is proportionally faster for short
+queries. Last-token pooling under the causal mask is right-pad safe (real tokens never attend to
+trailing pads), so the host just right-pads to the grid.
+
+## Host recipe (everything else is in-graph)
+
+- **Query** → prepend the instruction prefix:
+  `Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:`
+  **Document** → no prefix.
+- Tokenize, **right-pad** to 512 (truncate longer text). Run → 1024-d unit vector.
+- **Similarity** = cosine = dot product (vectors are unit-norm).
+- **Matryoshka (MRL)**: to shrink, take the first D dims (32 ≤ D ≤ 1024) and **re-L2-normalize**
+  on the host. Rankings are preserved down to 256; verified to 128.
+
+```python
+# Core AI runtime (Python), GPU delegate
+import coreai.runtime as rt, numpy as np
+from transformers import AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("tokenizer")
+m = await rt.AIModel.load("qwen3-embedding-0.6b_float16_s512_static.aimodel",
+        rt.SpecializationOptions.from_preferred_compute_unit_kind(rt.ComputeUnitKind.gpu()))
+fn = m.load_function("main")
+
+def embed(text, is_query):
+    prefix = ("Instruct: Given a web search query, retrieve relevant passages that "
+              "answer the query\nQuery:") if is_query else ""
+    enc = tok(prefix + text, padding="max_length", truncation=True, max_length=512,
+              return_tensors="np", padding_side="right")
+    res = await fn({"input_ids": rt.NDArray(enc["input_ids"].astype(np.int32)),
+                    "attention_mask": rt.NDArray(enc["attention_mask"].astype(np.int32))})
+    return res["embedding"].numpy()[0]   # [1024], unit-norm
+```
+
+### Swift — [CoreAIKit](https://github.com/john-rocky/coreai-kit)
+
+Downloads this repo on first use and applies the prompts in-process:
+
+```swift
+import CoreAIKitEmbeddings
+
+let embedder = try await TextEmbedder(model: .qwen3Embedding0_6B, prompts: .qwen3Embedding)
+let query = try await embedder.embed(query: "What is the capital of Japan?")
+let doc   = try await embedder.embed(document: "Tokyo is the capital and largest city of Japan.")
+let score = TextEmbedder.cosineSimilarity(query, doc)   // unit vectors → dot product = cosine
+```
+
+## Bundle layout
+
+```
+qwen3-embedding-0.6b_float16_s512_static.aimodel   (~1.1 GB, fp16)
+tokenizer/                                          (HF tokenizer files)
+reference.json                                      (torch reference embeddings + cosines)
+```
+
+## Parity
+
+Precision **fp16**. Verified against the official `sentence-transformers` pipeline (fp32):
+per-text embedding cosine **1.000000**, retrieval order identical, MRL rankings preserved at
+512 / 256 / 128. On the Core AI GPU delegate the `.aimodel` reproduces the torch reference at
+cosine **0.999998** end-to-end (host tokenize → run). Measured ~25 ms (256-grid) / ~45 ms
+(512-grid) per embedding on an M4 Max GPU.
+
+## License
+
+Apache-2.0 (upstream model and code are Apache-2.0). Conversion script:
+[`conversion/export_qwen3_embedding.py`](https://github.com/john-rocky/coreai-model-zoo/blob/main/conversion/export_qwen3_embedding.py)
+in the coreai-model-zoo.

qwen3-embedding-0.6b_float16_s512_static.aimodel/main.hash

@@ -0,0 +1 @@
+B

qwen3-embedding-0.6b_float16_s512_static.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420dd36581e8feb1afed13b8f6212b89d2e06573c2c8933d4d36e8623f89735f
+size 1192497696

qwen3-embedding-0.6b_float16_s512_static.aimodel/metadata.json

@@ -0,0 +1,7 @@
+{
+  "description" : "Qwen3-Embedding-0.6B text embedding model (Qwen3-0.6B backbone, last-token pooling, L2-normalized 1024-d, MRL-truncatable 32-1024). Source: https:\/\/huggingface.co\/Qwen\/Qwen3-Embedding-0.6B",
+  "creationDate" : "20260614T050108Z",
+  "author" : "Alibaba Qwen",
+  "assetVersion" : "2.0",
+  "license" : "Apache-2.0"
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b325f4efa94e389220ec20b055177a846870f4614762b59b1d6c7450c2830ec
+size 11423979

tokenizer/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}