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 +1,82 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+license: apache-2.0
+language:
+- en
+tags:
+- lora
+- transformers
+- style-transfer
+- copywriting
+---
+
+# pickbits-voice-daily-v1
+
+A LoRA adapter that writes in the house voice of [PickBits Daily Signal](https://pickbits.ai),
+trained on ~4 months of shipped, human-approved editorial content. Style-transfer proof of
+concept: the adapter reliably reproduces the publication's register, structure, and cadence on
+unseen topics, where the base model produces generic (often wrong-genre) text.
+
+- **Base model:** Qwen/Qwen2.5-1.5B-Instruct (frozen; this repo contains only the adapter)
+- **Method:** plain bf16 LoRA — r=16, alpha=32, dropout 0.05, targeting
+  q/k/v/o + gate/up/down projections (18.46M trainable params, 1.18% of base)
+- **Data:** 815 chat-format pairs harvested from shipped content (94 daily editions:
+  story sections, tl;dr bullets, standfirsts; plus devlog social captions).
+  40 pairs from the newest publication dates held out — zero date leakage.
+- **Training:** 3 epochs / 153 steps, lr 1e-4 cosine, effective batch 16, max_len 1024,
+  assistant-only loss masking. 19.5 min on a single RTX 3080 Ti (12 GB). Loss 2.98 → 2.39.
+
+## Before / after (held-out prompt, never seen in training)
+
+Prompt: *Engine: daily-signal / Task: story section / Heading: "Google put a deepfake button
+on the whole planet — then yanked it inside a day." / Seed: "The tool didn't invent fakery…"*
+
+**Base Qwen2.5-1.5B-Instruct:**
+> In an era where truth was as elusive as a shadow cast by a passing cloud, humanity found
+> itself at the mercy of an unprecedented technology…
+
+(Dystopian fiction — wrong genre entirely.)
+
+**With this adapter:**
+> The tool didn't invent fakery; it let a lie inherit the credibility of the real map
+> underneath it. On Monday, August 1, Google's…
+
+(Correct genre, register, and house structure: seed-line opener, declarative key-fact cadence.)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen2.5-1.5B-Instruct"
+tok = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(base, dtype=torch.bfloat16, device_map="auto")
+model = PeftModel.from_pretrained(model, "MrPIck/pickbits-voice-daily-v1")
+
+messages = [
+    {"role": "system", "content": "You are the PickBits staff writer. Write in the house voice."},
+    {"role": "user", "content": "Engine: daily-signal\nTask: tldr bullet\nSeed: EU AI Act enforcement began today with..."},
+]
+ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=False).to(model.device)
+out = model.generate(ids, max_new_tokens=400, temperature=0.7, top_p=0.9, do_sample=True)
+print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))
+```
+
+## Limitations
+
+- **Style, not knowledge.** Prompts in training carried only a heading and seed sentence, so
+  the adapter learned voice and structure — it will confidently invent facts. Feed real
+  source facts in the prompt; let the adapter supply only the how, not the what.
+- Trained for specific task framings (`Engine: daily-signal`, `Task: story section |
+  tldr bullet | edition standfirst`); other prompt shapes are out of distribution.
+- English only; single narrow editorial voice by design.
+
+## Provenance
+
+Training data is proprietary shipped editorial content from PickBits (not included in this
+repo). Adapter weights only. Built as a one-off proof of concept for a
+harvest → pairs → LoRA → held-out-eval pipeline, 2026-08-09.

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "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,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbad714429e5bd30c5af0790ceac0527bb198a0ab344fdefc316d159215c71e0
+size 73911112

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 %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
+size 11421991

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
+}