Upload folder using huggingface_hub

.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
+quantization_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+base_model: allura-forge/q3-30b-rc3
+library_name: transformers
+tags:
+- mergekit
+- axolotl
+- unsloth
+- roleplay
+- conversational
+datasets:
+- PygmalionAI/PIPPA
+- Alfitaria/nemotron-ultra-reasoning-synthkink
+- PocketDoc/Dans-Prosemaxx-Gutenberg
+- FreedomIntelligence/Medical-R1-Distill-Data
+- cognitivecomputations/SystemChat-2.0
+- allenai/tulu-3-sft-personas-instruction-following
+- kalomaze/Opus_Instruct_25k
+- simplescaling/s1K-claude-3-7-sonnet
+- ai2-adapt-dev/flan_v2_converted
+- grimulkan/theory-of-mind
+- grimulkan/physical-reasoning
+- nvidia/HelpSteer3
+- nbeerbower/gutenberg2-dpo
+- nbeerbower/gutenberg-moderne-dpo
+- nbeerbower/Purpura-DPO
+- antiven0m/physical-reasoning-dpo
+- allenai/tulu-3-IF-augmented-on-policy-70b
+- NobodyExistsOnTheInternet/system-message-DPO
+---
+
+# Q3-30B-A3B-Designant
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/6685d39f64da708c0f553c5d/1yVqoNrokaI2JbrjcCk1W.png" title="Made with NovelAI 4.5 Curated" width="750" height="750"></img>
+
+[*She looked into His Spine, into His Heart; and she saw there the shade of His soul.*](https://www.youtube.com/watch?v=bautietoaBo)
+
+# Overview
+
+Intended as a direct upgrade to [Pentiment](https://huggingface.co/allura-org/Q3-30b-A3b-Pentiment), ***Q3-30B-A3B-Designant*** is a roleplaying model finetuned from [Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base).
+
+During testing, Designant punched well above its weight class in terms of active parameters, demonstrating the potential for well-made lightweight Mixture of Experts models in the roleplay scene. While one tester observed looping behavior, repetition in general was minimal.
+
+# Quantizations
+
+GGUF:
+- [bartowski imatrixed quants](https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF)
+
+MLX:
+- [8bpw](https://huggingface.co/soundTeam/Q3-30B-A3B-Designant_mlx-8bpw)
+
+# Usage
+
+- Format is plain-old ChatML (please note that, unlike regular Qwen 3, you do *not* need to prefill empty think tags for it not to reason -- see below).
+
+- Settings used by testers varied, but Fizz and inflatebot used the same settings and system prompt recommended for [GLM4-32B-Neon-v2.](https://huggingface.co/allura-org/GLM4-32B-Neon-v2)
+
+- The instruction following version of Qwen3-30B-A3B was not part of the merge. Instruction-following is trained in post-hoc, and "thinking" data was not included. __As a result of this, "thinking" will likely not function as intended.__
+
+- As with any Q3-30B-A3B, Designant performs very adequately with few or zero layers offloaded to GPU. When using the [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp) server, a 7950X CPU with 32GB of DDR5 RAM can run a Q4_K_M quant of this architecture at ~15 tokens/sec *with no GPU involved at all.*
+
+# Training Process
+
+1. The [base model](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base) first went through a supervised finetune on a corpus of instruction following data, roleplay conversations, and human writing based on the [Ink](https://huggingface.co/collections/allura-org/ink-6772fd1442308781594bbabb)/[Bigger Body](https://huggingface.co/collections/allura-org/bigger-body-67b277af0861cec33b54745d)/[Remnant](https://huggingface.co/collections/allura-org/remnant-6817c2113bbb2aed501513d0) lineage.
+
+2. It was then slightly merged with [Pantheon-Proto-RP-1.8](https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B), to improve stability.
+
+3. Finally, a KTO reinforcement learning phase steered the model away from the very purple prose the initial merge had, and improved its logical+spatial reasoning and sense of overall "intelligence".
+
+# Credits
+
+- Fizz - Train, Merge, Data Wrangling
+
+- Toaster, OMGWTFBBQ, The Trashpanda Testing Crew - Testing
+
+- inflatebot - Model Card, Testing, Merging Consultation
+
+- Juahyori, Artus - Compute Funding
+
+- Gryphe, Alibaba - Making the original models as well as the ones used in the merge
+
+Bot would like to thank the Allura community on Discord, especially Curse, Vagabond, Artus and Mawnipulator, for their companionship and moral support. You all mean the world to us.
+
+---
+<sup>*`There, God is not.`*</sup>

config.json

@@ -0,0 +1,49 @@
+{
+    "architectures": [
+        "Qwen3MoeForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "eos_token_id": 151643,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 48,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_moe",
+    "moe_intermediate_size": 768,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 4,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.3",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936,
+    "quantization_config": {
+        "quant_method": "exl3",
+        "version": "0.0.2",
+        "bits": 6.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "cols": 2048
+        },
+        "out_scales": "auto"
+    }
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+base_model: Qwen/Qwen3-30B-A3B-Base
+models:
+  - model: allura-forge/q3-30b-ft-ep2-merged
+    parameters:
+      weight: 0.75
+      density: 0.9
+  - model: Gryphe/Pantheon-Proto-RP-1.8-30B-A3B
+    parameters:
+      weight: 0.25
+      density: 0.5
+merge_method: ties
+dtype: bfloat16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373f4036e0b78c45f4dbe27ece8d79d0b302f268f42ec3e3e913551e220ee057
+size 8142456856

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f7b520e05ffa8494c35ed29305997861b31c5ff63ae1cfcd72fa91c6e5a26d
+size 8460120016

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b05df55c40d1574967b37f18ad11ff937da804e8ef5d174c52b539ecf3765b
+size 6813778528

quantization_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3214b9f8ab422aa500c7aea882b4f8ea3b05351329da156197157009bbea2605
+size 18444906

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}