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

README.md

@@ -0,0 +1,98 @@
+---
+license: cc-by-nc-4.0
+base_model: Qwen/Qwen3-0.6B
+library_name: bev-decider
+base_model_relation: finetune
+datasets:
+  - avbiswas/bev-decision-150K
+pipeline_tag: text-classification
+tags:
+  - system-one
+  - decision-model
+  - jev-compatible
+language:
+  - en
+---
+
+# jev-decider-0.4B
+
+A **0.4B-parameter System One decision model** in the bev-decider / Jev format. It reads a state (text or JSON) and typed questions about it and returns probabilities in a single forward pass, with no text generation:
+
+- **`choice`**: pick one of several named options.
+- **`noul`**: yes/no, returned as P(yes).
+- **`score`**: an ordinal level, returned as the expected value over the levels.
+
+## Architecture
+
+This is a single self-contained model. `model.safetensors` holds the whole network in one file.
+
+| | |
+|---|---|
+| Backbone | The first **20 of 28 layers** of [`Qwen/Qwen3-0.6B`](https://huggingface.co/Qwen/Qwen3-0.6B), with the fine-tuned LoRA (r=8, alpha=16 on `q/k/v/o_proj` of layers 8–19) **merged** into the weights |
+| Decision head | 2-layer attention head, 512-dim, with a task-type embedding |
+| Parameters | ≈ 0.4B (0.31B in the transformer layers, 0.16B token embeddings, 7.4M head) |
+| Weights | `model.safetensors` (bf16 backbone + fp32 head), plus `backbone_config.json`, `config.json` and Qwen's tokenizer files |
+| Context | Trained with states up to **512** tokens; options are limited to 64 tokens each |
+
+The head is a custom module, so the model is loaded with the [`bev-decider`](https://github.com/avbiswas/bev-decider) package.
+
+## Usage
+
+Install the `bev-decider` package, which downloads this model on first use:
+
+```bash
+pip install bev-decider
+from bev_decider import load
+
+decider = load("NeelContractor/jev-decider-0.4B")
+
+state = {
+    "message": (
+        "URGENT: you charged my card twice this month. "
+        "Refund the duplicate within 24 hours or I'm disputing it with my bank."
+    )
+}
+
+questions = {
+    "intent": {
+        "type": "choice",
+        "instructions": "What does the customer want?",
+        "criteria": {
+            "refund": "money returned or a duplicate charge reversed",
+            "technical_help": "a bug, outage or integration problem",
+            "cancellation": "wants to cancel or downgrade",
+        },
+    },
+    "urgent": {
+        "type": "noul",
+        "instructions": "Does the message communicate time pressure or a deadline?",
+    },
+    "anger": {
+        "type": "score",
+        "instructions": "How angry is the customer?",
+        "criteria": ["calm", "mildly annoyed", "frustrated", "furious"],
+    },
+}
+
+print(decider.decide(state, questions))
+Evaluation
+Held-out test split of avbiswas/bev-decision-150K (https://huggingface.co/datasets/avbiswas/bev-decision-150K),
+2,000 questions, single forward pass:
+Metric	Value
+Accuracy (all)	0.7300
+Yes/no (noul)	0.8178
+Choice	0.7192
+Score	0.5964
+AUC (noul)	0.8859
+These numbers come from the best checkpoint (step 1000 of the final run) selected by test accuracy.
+Training
+- Base: first 20 layers of Qwen/Qwen3-0.6B (weights frozen except LoRA).
+- LoRA: r=8, alpha=16, dropout 0, on q/k/v/o_proj of layers 8–19.
+- Head: 2 attention blocks, 512-dim, num_task_types=3 (choice, noul, score).
+- Data: avbiswas/bev-decision-150K (250,262 exploded training questions).
+- Objective: cross-entropy over the options.
+- Precision: bf16 autocast, fp32 head. Optimizer: AdamW (head lr 1e-3, LoRA lr 1e-4).
+The exported weights are the LoRA-merged backbone plus the trained head.
+License
+The model is CC-BY-NC-4.0 (non-commercial), because the training data includes sources with non-commercial terms. It contains weights derived from
+Qwen3-0.6B (https://huggingface.co/Qwen/Qwen3-0.6B), which is Apache-2.0; Qwen's license is included as LICENSE-Qwen.

backbone_config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 20,
+  "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": "5.19.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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 +1,43 @@
+{
+  "model_type": "bev-decider",
+  "version": "0.4.0",
+  "format": "merged",
+  "backbone_config": "backbone_config.json",
+  "backbone_dtype": "bf16",
+  "num_layers": 20,
+  "head": {
+    "new_dim": 512,
+    "num_layers": 2,
+    "num_task_types": 3
+  },
+  "task_types": {
+    "choice": 0,
+    "noul": 1,
+    "score": 2
+  },
+  "max_state_tokens_train": 512,
+  "max_state_tokens": 512,
+  "max_choice_tokens": 64,
+  "source_checkpoint": "best",
+  "derived_from": {
+    "base_model": "Qwen/Qwen3-0.6B",
+    "lora": {
+      "r": 8,
+      "alpha": 16,
+      "layers": [
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc59c856f60714b3985749d24b8017b8ca89636cdda44dd0c91142db342d3645
+size 969892784

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
+}