Upload folder using huggingface_hub

README.md

@@ -24,10 +24,33 @@ The **AskBeforeAnswer** model exhibits "clarification-seeking" behavior. When pr
 
 ## Pipeline
 - **Base Model:** Qwen/Qwen2.5-7B-Instruct
-- **Stage 1 (SFT):** Aligned to output structured JSON indicating `Action: Clarify` or `Action: Answer`.
-- **Stage 2 (DPO):** Preference optimized to strongly penalize hallucinations on ambiguous queries, using `chrisjcc/ask-before-answer-data`.
+- **Ablation Winner:** The model variant promoted to Production via W&B Registry is: 
+  `dpo`.
 
-**GitHub Release:** [v0.0.4](https://github.com/chrisjcc/ask-before-answer/releases/tag/v0.0.4)
+## LLM-as-a-Judge Evaluation Leaderboard
+
+The following scores were computed using W&B Weave with a 
+Gemini-based judge scorer on a randomly selected 
+**50-sample** subset 
+of the `sewon/ambig_qa` (validation split).
+
+| Metric                |      base |   dpo_only |      sft |   sft_dpo |   clarifier_lora |
+|:----------------------|----------:|-----------:|---------:|----------:|-----------------:|
+| ambiguity_detection   | 0.978     |   0.964    | 0.972    |  0.976    |          0.998   |
+| clarification_quality | 0.786     |   0.798    | 0.798    |  0.8      |          0.796   |
+| usefulness            | 0.882     |   0.896    | 0.9      |  0.9      |          0.896   |
+| model_accuracy        | 0.62      |   0.64     | 0.66     |  0.62     |          0.6     |
+| clarify_precision     | 0.617021  |   0.642857 | 0.675676 |  0.627907 |          0.6     |
+| clarify_recall        | 0.966667  |   0.9      | 0.833333 |  0.9      |          1       |
+| clarify_f1            | 0.753247  |   0.75     | 0.746269 |  0.739726 |          0.75    |
+| answer_f1             | 0.173913  |   0.357143 | 0.484848 |  0.296296 |          0       |
+| macro_f1              | 0.46358   |   0.553571 | 0.615559 |  0.518011 |          0.375   |
+| answer_accuracy       | 0.05      |   0.1      | 0.1      |  0.1      |          0       |
+| facet_generation_rate | 0.0212766 |   1        | 1        |  1        |          0       |
+| clarify_ratio         | 1.56667   |   1.4      | 1.23333  |  1.43333  |          1.66667 |
+
+
+**GitHub Release:** [v0.0.5](https://github.com/chrisjcc/ask-before-answer/releases/tag/v0.0.5)
 
 ## Usage
 ```python

adapter_config.json

@@ -1,8 +1,18 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit",
   "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -10,25 +20,33 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.05,
+  "lora_ga_config": null,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "v_proj",
     "up_proj",
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
     "gate_proj",
-    "q_proj"
+    "down_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2105bf29ad1a8dbfdb62a62d48753adc3605d0268888215f6a7963842103269
-size 323014168
+oid sha256:3364d7db681c91edc6f1472dc8aadcc78c3b67818698637a5905f6b1119ed1e7
+size 161533192

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -195,12 +195,13 @@
     "<|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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd538fde958b3b6e543be7489246bfa5e8b154dacd9d2cb8d020175cb7b43478
-size 6072
+oid sha256:e6a9bd126ecf9622ab5ea9a23d1c94aee8867a878b948495e4a44f5f688da737
+size 6584