Add MLX 4-bit quantized weights + model card

.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 +1,137 @@
+---
+license: apache-2.0
+base_model:
+  - KyleHessling1/Qwopus-GLM-18B-Healed
+  - Jackrong/Qwopus3.5-9B-v3.5
+  - Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1
+tags:
+  - mlx
+  - mlx-4bit
+  - quantized
+  - apple-silicon
+  - merge
+  - frankenmerge
+  - qwen3.5
+  - reasoning
+  - text-generation
+  - conversational
+  - unsloth
+  - agent
+  - tool-use
+  - chain-of-thought
+library_name: mlx
+model_type: qwen3_5
+pipeline_tag: text-generation
+language:
+  - en
+  - zh
+  - ko
+  - ja
+  - fr
+  - de
+  - es
+---
+
+# Qwopus-GLM-18B-Healed — MLX 4-bit
+
+**Apple Silicon / MLX 4-bit quantization** of the healed Qwopus-GLM-18B frankenmerge. Ready to run on Macs with the [MLX](https://github.com/ml-explore/mlx) framework via [`mlx-lm`](https://github.com/ml-explore/mlx-lm).
+
+- **Source (BF16):** [KyleHessling1/Qwopus-GLM-18B-Healed](https://huggingface.co/KyleHessling1/Qwopus-GLM-18B-Healed)
+- **Q4_K_M GGUF (llama.cpp):** [KyleHessling1/Qwopus-GLM-18B-Merged-GGUF](https://huggingface.co/KyleHessling1/Qwopus-GLM-18B-Merged-GGUF)
+
+## Quickstart
+
+```bash
+pip install -U "mlx-lm>=0.31.2"
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("KyleHessling1/Qwopus-GLM-18B-Healed-MLX-4bit")
+print(generate(model, tokenizer, prompt="The capital of France is", max_tokens=64))
+```
+
+Or from the CLI:
+
+```bash
+python3 -m mlx_lm generate \
+  --model KyleHessling1/Qwopus-GLM-18B-Healed-MLX-4bit \
+  --prompt "Write a haiku about Apple Silicon." \
+  --max-tokens 128
+```
+
+Runs comfortably on a 16–24 GB unified-memory Mac (M-series).
+
+## Quantization
+
+| Property | Value |
+|---|---|
+| **Method** | MLX affine quantization (`mlx_lm.convert -q`) |
+| **Bits / weight** | 4 (effective **4.502** after non-quantized layers) |
+| **Group size** | 64 |
+| **Non-quant dtype** | bfloat16 |
+| **Output size** | **~8.4 GB** (2 safetensor shards) |
+| **Quantizer version** | `mlx-lm` 0.31.2 / `mlx` 0.31.1 |
+
+Reproducible from the BF16 source with:
+
+```bash
+python3 -m mlx_lm convert \
+  --hf-path KyleHessling1/Qwopus-GLM-18B-Healed \
+  --mlx-path ./Qwopus-GLM-18B-Healed-MLX-4bit \
+  -q --q-bits 4 --q-group-size 64
+```
+
+## Base Model
+
+A **64-layer frankenmerge** of two of [Jackrong's](https://huggingface.co/Jackrong) Qwen3.5-9B finetunes, healed with a 1000-step QLoRA fine-tune:
+
+- **Layers 0–31:** [Jackrong/Qwopus3.5-9B-v3.5](https://huggingface.co/Jackrong/Qwopus3.5-9B-v3.5) (Opus reasoning distill)
+- **Layers 32–63:** [Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1](https://huggingface.co/Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1) (GLM-5.1 reasoning distill)
+- **Heal training:** 1000 steps QLoRA (rank 64) on Jackrong's training data to smooth the layer boundary
+
+### Architecture
+
+| Property | Value |
+|---|---|
+| **Parameters** | ~18B |
+| **Layers** | 64 (32 + 32) |
+| **Hidden Size** | 4096 |
+| **Attention Heads** | 16 (4 KV heads, GQA) |
+| **Attention Type** | Hybrid (linear + full, every 4th layer) |
+| **Context Length** | 262,144 tokens |
+| **Source Precision** | BF16 |
+
+### Capability Suite (from base model)
+
+Beats Qwen 3.6-35B-A3B MoE on a 44-test capability suite at less than half the VRAM:
+
+| | Qwopus-GLM-18B (healed) | Qwen 3.6-35B MoE |
+|---|---|---|
+| **Score** | **40/44 (90.9%)** | 38/44 (86.4%) |
+| **Tool Calling** | 6/6 | 6/6 |
+| **Agentic** | 4/4 | 4/4 |
+| **Programming** | 12/15 | 12/15 |
+
+Frontend stress tests: **62/63 checks passed** across 6 complex HTML/CSS/JS generation tasks with perfectly balanced braces/parens and zero garbled output.
+
+> Note: benchmarks were measured on the BF16 base / Q4_K_M GGUF. The MLX 4-bit weights are a separate quantization and have not been independently re-benchmarked — expect quality within normal 4-bit quantization variance.
+
+## Known Issues
+
+- The tokenizer emits a Mistral-regex warning on load (inherited from the source repo). Benign for Qwen tokenization in practice.
+
+## Credits
+
+All credit for the source models goes to **[Jackrong](https://huggingface.co/Jackrong)**. The heal training used his published datasets. See the [full merge documentation](https://huggingface.co/KyleHessling1/Qwopus-GLM-18B-Merged-GGUF/blob/main/MERGE_PROCESS.md) for the complete technical workflow.
+
+MLX quantization by [@KyleHessling1](https://huggingface.co/KyleHessling1) using [mlx-lm](https://github.com/ml-explore/mlx-lm).
+
+## License
+
+Apache 2.0 (inherited from source models)
+
+## Contact
+
+Questions, issues, or cool projects? Reach out on X: [@KyleHessling1](https://x.com/KyleHessling1)

chat_template.jinja

@@ -0,0 +1,88 @@
+{%- 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
+<think>
+' }}
+{%- endif %}

config.json

@@ -0,0 +1,139 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "eos_token_id": 248046,
+    "image_token_id": 248056,
+    "model_name": "/home/kylehessling/models/Qwopus-GLM-18B-merged",
+    "model_type": "qwen3_5",
+    "pad_token_id": 248055,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": null,
+        "torch_dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 12288,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 64,
+        "num_key_value_heads": 4,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.6",
+    "use_cache": false,
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1958be7d29393269f7bd108590995d0242cc7fc7465907543d7beda5ce55da8
+size 5354562558

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5015fba0ed2bb901d3697d5a8b6923660b8eedaede6876cbd9d6f1c4b7faa7bd
+size 3577494967

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "max_length": 4096,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "json_tools",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}