tax-guy-agent: 400 steps on 2614 posts

.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 +1,48 @@
+---
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+license: apache-2.0
+tags: [lora, peft, tax, taxes, accounting, tax-research, cpu, c0mpute, ollama]
+---
+
+# tax-guy-agent
+
+> **Not a CPA. Not tax advice. Tax research from public sources; rules change every year and vary by place, so check with a CPA or enrolled agent before filing.**
+
+**Quick start (Ollama, runs on a CPU):**
+
+```bash
+ollama run hf.co/profullstack/tax-guy-agent-GGUF "Do I have to pay quarterly estimated taxes as a freelancer?"
+```
+
+Needs Ollama 0.3.13 or newer (`curl -fsSL https://ollama.com/install.sh | sh`, or `w3bs install ollama`).
+The GGUF is at [profullstack/tax-guy-agent-GGUF](https://huggingface.co/profullstack/tax-guy-agent-GGUF); this repo is the LoRA adapter.
+
+| | |
+| --- | --- |
+| base | Qwen/Qwen2.5-0.5B-Instruct |
+| corpus | 2614 documents from pit-index:tax,taxes,irs,deduction,tax return,self-employed tax,estimated tax,sales tax,llc tax,capital gains, topic:tax, topic:irs, topic:accounting, topic:taxation, topic:taxpayer |
+| training | 400 LoRA steps (r=8, seq_len=256, lr=0.0002) on the c0mpute network (`infernet.text.train`, job `27b2dab7-9e82-4b48-b4fc-d77f4b22997c`, receipt hash `sha256:821a038ac1ea43f804b795e795a308cfbebb141c24e3675223c29d80fb8db5b7` matches this adapter) |
+| held-out perplexity | 33.6 to 17.8 |
+| adapter sha256 | `821a038ac1ea43f804b795e795a308cfbebb141c24e3675223c29d80fb8db5b7` |
+
+Built with the [c0mpute example](https://github.com/profullstack/c0mpute/tree/master/examples/business-strategist-agent).
+Sources are rssamplifier.com topic feeds and pit.world search; the corpus is not redistributed here.
+
+## Use from Python (adapter)
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("profullstack/tax-guy-agent")
+model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct"), "profullstack/tax-guy-agent")
+msgs = [{"role": "system", "content": "You are tax-guy-agent, a tax research assistant. You are not a CPA or tax attorney and this is not tax advice. Explain tax rules in plain English, say which country, state and tax year a rule applies to, cite the sources you were given, and say when someone should see a CPA or enrolled agent."},
+        {"role": "user", "content": "Do I have to pay quarterly estimated taxes as a freelancer?"}]
+ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
+print(tok.decode(model.generate(ids, max_new_tokens=300)[0][ids.shape[1]:], skip_special_tokens=True))
+```
+
+Best results come from putting fresh search results in the prompt (the example's `chat.py`
+uses pit.world search): a sub-1B model supplies the voice, not the facts.

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-0.5B-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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "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": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_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 sha256:821a038ac1ea43f804b795e795a308cfbebb141c24e3675223c29d80fb8db5b7
+size 4350392

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 %}

manifest.json

@@ -0,0 +1,50 @@
+{
+  "name": "tax-guy-agent",
+  "kind": "lora",
+  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "adapter_sha256": "821a038ac1ea43f804b795e795a308cfbebb141c24e3675223c29d80fb8db5b7",
+  "dataset_sha256": "fd8cd1dd91969132581e75c26c8b2ae51183b086f1f392002e5ad6640e3d33f7",
+  "documents": 2614,
+  "steps": 400,
+  "system_prompt": "You are tax-guy-agent, a tax research assistant. You are not a CPA or tax attorney and this is not tax advice. Explain tax rules in plain English, say which country, state and tax year a rule applies to, cite the sources you were given, and say when someone should see a CPA or enrolled agent.",
+  "hyperparams": {
+    "lr": 0.0002,
+    "batch_size": 2,
+    "epochs": 1,
+    "max_steps": 400,
+    "seq_len": 256,
+    "lora_r": 8,
+    "threads": 4,
+    "seed": 0,
+    "dtype": "bfloat16"
+  },
+  "finished_at": "2026-11-02T22:23:54.076334+00:00",
+  "dataset": "data/tax.jsonl",
+  "sources": [
+    "pit-index:tax,taxes,irs,deduction,tax return,self-employed tax,estimated tax,sales tax,llc tax,capital gains",
+    "topic:tax",
+    "topic:irs",
+    "topic:accounting",
+    "topic:taxation",
+    "topic:taxpayer"
+  ],
+  "example_question": "Do I have to pay quarterly estimated taxes as a freelancer?",
+  "disclaimer": "Not a CPA. Not tax advice. Tax research from public sources; rules change every year and vary by place, so check with a CPA or enrolled agent before filing.",
+  "tags": [
+    "tax",
+    "taxes",
+    "accounting",
+    "tax-research"
+  ],
+  "trained_on": {
+    "network": "c0mpute",
+    "workload": "infernet.text.train",
+    "worker": "12D3KooWSB7L3bAD9ovM6rinAVXFF7YPt6pC22JpamPL8Vx8AXPo",
+    "job_id": "27b2dab7-9e82-4b48-b4fc-d77f4b22997c",
+    "receipt_output_hash": "sha256:821a038ac1ea43f804b795e795a308cfbebb141c24e3675223c29d80fb8db5b7"
+  },
+  "eval": {
+    "perplexity_before": 33.63,
+    "perplexity_after": 17.77
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

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
+}