Replace model merge with direct adapter push to HF Hub

- Skip merge_and_unload which causes peft/accelerate TypeError on T4
- Push LoRA adapter + tokenizer directly via HfApi.upload_folder
- Update inference test to load adapter with PeftModel.from_pretrained
- Remove redundant push cell

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

notebooks/ch_trader_finetune.ipynb

@@ -1244,14 +1244,14 @@
   },
   {
    "cell_type": "markdown",
-   "source": "## 5. Save & Push to HuggingFace Hub\n\nMerges LoRA adapters into the base model weights and pushes the full model.",
+   "source": "## 5. Save & Push to HuggingFace Hub\n\nPushes the LoRA adapter and tokenizer directly to HuggingFace Hub.\nThe adapter can be loaded at inference time with `PeftModel.from_pretrained()` — merging into the base model is not required and avoids OOM on T4.",
    "metadata": {
     "id": "save-header"
    }
   },
   {
    "cell_type": "code",
-   "source": "from peft import PeftModel\n\n# Reload base model in fp16 for merging (can't merge with 4-bit)\nprint(\"Reloading base model in fp16 for adapter merge...\")\ndel model\ntorch.cuda.empty_cache()\n\nbase_model = AutoModelForCausalLM.from_pretrained(\n    BASE_MODEL,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n    trust_remote_code=True,\n)\nmerged_model = PeftModel.from_pretrained(base_model, OUTPUT_DIR)\nmerged_model = merged_model.merge_and_unload()\nprint(\"Adapters merged.\")",
+   "source": "from huggingface_hub import HfApi\n\n# Tokenizer was already saved in the training cell; ensure it's there\ntokenizer.save_pretrained(OUTPUT_DIR)\n\n# Push adapter + tokenizer to HF Hub\napi = HfApi(token=HF_TOKEN)\napi.upload_folder(\n    folder_path=OUTPUT_DIR,\n    repo_id=OUTPUT_REPO,\n    commit_message=f\"StockEx CH Trader: QLoRA fine-tuned {BASE_MODEL} (adapter)\",\n)\nprint(f\"Pushed to https://huggingface.co/{OUTPUT_REPO}\")",
    "metadata": {
     "id": "save-model",
     "trusted": true
@@ -1259,16 +1259,6 @@
    "outputs": [],
    "execution_count": null
   },
-  {
-   "cell_type": "code",
-   "source": "print(f\"Pushing merged model to: {OUTPUT_REPO}\")\nmerged_model.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"StockEx CH Trader: QLoRA fine-tuned Qwen2.5-32B-Instruct\",\n)\ntokenizer.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"Tokenizer for StockEx CH Trader (Qwen2.5-32B-Instruct base)\",\n)\nprint(f\"✓ Model pushed to https://huggingface.co/{OUTPUT_REPO}\")",
-   "metadata": {
-    "id": "push-hub",
-    "trusted": true
-   },
-   "outputs": [],
-   "execution_count": null
-  },
   {
    "cell_type": "markdown",
    "source": "## 6. Inference Test\n\nVerify the model generates valid JSON trading decisions.",
@@ -1278,7 +1268,7 @@
   },
   {
    "cell_type": "code",
-   "source": "import re\nfrom transformers import pipeline\n\npipe = pipeline(\n    \"text-generation\",\n    model=merged_model,\n    tokenizer=tokenizer,\n    device_map=\"auto\",\n)\n\ntest_cases = [\n    {\n        \"desc\": \"New member, no holdings, must trade\",\n        \"capital\": 100_000.0,\n        \"holdings\": [],\n        \"obligation\": 10,\n    },\n    {\n        \"desc\": \"Experienced member with holdings, low obligation\",\n        \"capital\": 65_000.0,\n        \"holdings\": [\n            {\"symbol\": \"ALPHA\", \"quantity\": 300, \"avg_cost\": 5.60},\n            {\"symbol\": \"QUEST\", \"quantity\": 150, \"avg_cost\": 13.20},\n        ],\n        \"obligation\": 2,\n    },\n    {\n        \"desc\": \"Low capital, large holdings\",\n        \"capital\": 8_000.0,\n        \"holdings\": [\n            {\"symbol\": \"PEIR\",  \"quantity\": 500, \"avg_cost\": 8.30},\n            {\"symbol\": \"NBG\",   \"quantity\": 200, \"avg_cost\": 7.95},\n        ],\n        \"obligation\": 5,\n    },\n]\n\ntest_bbos = {s[\"symbol\"]: gen_bbo(s[\"base\"]) for s in SECURITIES}\n\nprint(\"=\" * 70)\nfor tc in test_cases:\n    print(f\"\\nSCENARIO: {tc['desc']}\")\n    prompt = build_prompt(\"USR01\", tc[\"capital\"], tc[\"holdings\"], tc[\"obligation\"], test_bbos)\n    messages = [\n        {\"role\": \"system\", \"content\": SYSTEM_PROMPT},\n        {\"role\": \"user\",   \"content\": prompt},\n    ]\n    output = pipe(\n        messages,\n        max_new_tokens=60,\n        temperature=0.3,\n        do_sample=True,\n        pad_token_id=tokenizer.eos_token_id,\n    )\n    response = output[0][\"generated_text\"][-1][\"content\"].strip()\n    print(f\"RESPONSE: {response}\")\n    try:\n        m = re.search(r\"\\{[^}]+\\}\", response)\n        if m:\n            d = json.loads(m.group())\n            assert d[\"side\"] in (\"BUY\", \"SELL\")\n            assert d[\"symbol\"] in [s[\"symbol\"] for s in SECURITIES]\n            assert d[\"quantity\"] > 0\n            assert d[\"price\"] > 0\n            print(f\"✓ Valid JSON: {d}\")\n        else:\n            print(\"✗ No JSON found in response\")\n    except Exception as e:\n        print(f\"✗ Invalid: {e}\")\n    print(\"-\" * 70)",
+   "source": "import re\nfrom transformers import pipeline\nfrom peft import PeftModel\n\n# Load adapter for inference test\nprint(\"Loading base model + adapter for inference test...\")\ndel trainer\ntorch.cuda.empty_cache()\n\nbase_model = AutoModelForCausalLM.from_pretrained(\n    BASE_MODEL,\n    quantization_config=BitsAndBytesConfig(\n        load_in_4bit=True,\n        bnb_4bit_quant_type=\"nf4\",\n        bnb_4bit_compute_dtype=torch.bfloat16,\n        bnb_4bit_use_double_quant=True,\n    ),\n    device_map=\"auto\",\n    trust_remote_code=True,\n)\ninference_model = PeftModel.from_pretrained(base_model, OUTPUT_DIR)\ninference_model.eval()\n\npipe = pipeline(\n    \"text-generation\",\n    model=inference_model,\n    tokenizer=tokenizer,\n    device_map=\"auto\",\n)\n\ntest_cases = [\n    {\n        \"desc\": \"New member, no holdings, must trade\",\n        \"capital\": 100_000.0,\n        \"holdings\": [],\n        \"obligation\": 10,\n    },\n    {\n        \"desc\": \"Experienced member with holdings, low obligation\",\n        \"capital\": 65_000.0,\n        \"holdings\": [\n            {\"symbol\": \"ALPHA\", \"quantity\": 300, \"avg_cost\": 5.60},\n            {\"symbol\": \"QUEST\", \"quantity\": 150, \"avg_cost\": 13.20},\n        ],\n        \"obligation\": 2,\n    },\n    {\n        \"desc\": \"Low capital, large holdings\",\n        \"capital\": 8_000.0,\n        \"holdings\": [\n            {\"symbol\": \"PEIR\",  \"quantity\": 500, \"avg_cost\": 8.30},\n            {\"symbol\": \"NBG\",   \"quantity\": 200, \"avg_cost\": 7.95},\n        ],\n        \"obligation\": 5,\n    },\n]\n\ntest_bbos = {s[\"symbol\"]: gen_bbo(s[\"base\"]) for s in SECURITIES}\n\nprint(\"=\" * 70)\nfor tc in test_cases:\n    print(f\"\\nSCENARIO: {tc['desc']}\")\n    prompt = build_prompt(\"USR01\", tc[\"capital\"], tc[\"holdings\"], tc[\"obligation\"], test_bbos)\n    messages = [\n        {\"role\": \"system\", \"content\": SYSTEM_PROMPT},\n        {\"role\": \"user\",   \"content\": prompt},\n    ]\n    output = pipe(\n        messages,\n        max_new_tokens=60,\n        temperature=0.3,\n        do_sample=True,\n        pad_token_id=tokenizer.eos_token_id,\n    )\n    response = output[0][\"generated_text\"][-1][\"content\"].strip()\n    print(f\"RESPONSE: {response}\")\n    try:\n        m = re.search(r\"\\{[^}]+\\}\", response)\n        if m:\n            d = json.loads(m.group())\n            assert d[\"side\"] in (\"BUY\", \"SELL\")\n            assert d[\"symbol\"] in [s[\"symbol\"] for s in SECURITIES]\n            assert d[\"quantity\"] > 0\n            assert d[\"price\"] > 0\n            print(f\"Valid JSON: {d}\")\n        else:\n            print(\"No JSON found in response\")\n    except Exception as e:\n        print(f\"Invalid: {e}\")\n    print(\"-\" * 70)",
    "metadata": {
     "id": "inference-test",
     "trusted": true

notebooks/stockex-clearing-house-llm-fine-tuning.ipynb

@@ -1244,14 +1244,14 @@
   },
   {
    "cell_type": "markdown",
-   "source": "## 5. Save & Push to HuggingFace Hub\n\nMerges LoRA adapters into the base model weights and pushes the full model.",
+   "source": "## 5. Save & Push to HuggingFace Hub\n\nPushes the LoRA adapter and tokenizer directly to HuggingFace Hub.\nThe adapter can be loaded at inference time with `PeftModel.from_pretrained()` — merging into the base model is not required and avoids OOM on T4.",
    "metadata": {
     "id": "save-header"
    }
   },
   {
    "cell_type": "code",
-   "source": "from peft import PeftModel\n\n# Reload base model in fp16 for merging (can't merge with 4-bit)\nprint(\"Reloading base model in fp16 for adapter merge...\")\ndel model\ntorch.cuda.empty_cache()\n\nbase_model = AutoModelForCausalLM.from_pretrained(\n    BASE_MODEL,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n    trust_remote_code=True,\n)\nmerged_model = PeftModel.from_pretrained(base_model, OUTPUT_DIR)\nmerged_model = merged_model.merge_and_unload()\nprint(\"Adapters merged.\")",
+   "source": "from huggingface_hub import HfApi\n\n# Tokenizer was already saved in the training cell; ensure it's there\ntokenizer.save_pretrained(OUTPUT_DIR)\n\n# Push adapter + tokenizer to HF Hub\napi = HfApi(token=HF_TOKEN)\napi.upload_folder(\n    folder_path=OUTPUT_DIR,\n    repo_id=OUTPUT_REPO,\n    commit_message=f\"StockEx CH Trader: QLoRA fine-tuned {BASE_MODEL} (adapter)\",\n)\nprint(f\"Pushed to https://huggingface.co/{OUTPUT_REPO}\")",
    "metadata": {
     "id": "save-model",
     "trusted": true
@@ -1259,16 +1259,6 @@
    "outputs": [],
    "execution_count": null
   },
-  {
-   "cell_type": "code",
-   "source": "print(f\"Pushing merged model to: {OUTPUT_REPO}\")\nmerged_model.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"StockEx CH Trader: QLoRA fine-tuned Qwen2.5-32B-Instruct\",\n)\ntokenizer.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"Tokenizer for StockEx CH Trader (Qwen2.5-32B-Instruct base)\",\n)\nprint(f\"✓ Model pushed to https://huggingface.co/{OUTPUT_REPO}\")",
-   "metadata": {
-    "id": "push-hub",
-    "trusted": true
-   },
-   "outputs": [],
-   "execution_count": null
-  },
   {
    "cell_type": "markdown",
    "source": "## 6. Inference Test\n\nVerify the model generates valid JSON trading decisions.",
@@ -1278,7 +1268,7 @@
   },
   {
    "cell_type": "code",
-   "source": "import re\nfrom transformers import pipeline\n\npipe = pipeline(\n    \"text-generation\",\n    model=merged_model,\n    tokenizer=tokenizer,\n    device_map=\"auto\",\n)\n\ntest_cases = [\n    {\n        \"desc\": \"New member, no holdings, must trade\",\n        \"capital\": 100_000.0,\n        \"holdings\": [],\n        \"obligation\": 10,\n    },\n    {\n        \"desc\": \"Experienced member with holdings, low obligation\",\n        \"capital\": 65_000.0,\n        \"holdings\": [\n            {\"symbol\": \"ALPHA\", \"quantity\": 300, \"avg_cost\": 5.60},\n            {\"symbol\": \"QUEST\", \"quantity\": 150, \"avg_cost\": 13.20},\n        ],\n        \"obligation\": 2,\n    },\n    {\n        \"desc\": \"Low capital, large holdings\",\n        \"capital\": 8_000.0,\n        \"holdings\": [\n            {\"symbol\": \"PEIR\",  \"quantity\": 500, \"avg_cost\": 8.30},\n            {\"symbol\": \"NBG\",   \"quantity\": 200, \"avg_cost\": 7.95},\n        ],\n        \"obligation\": 5,\n    },\n]\n\ntest_bbos = {s[\"symbol\"]: gen_bbo(s[\"base\"]) for s in SECURITIES}\n\nprint(\"=\" * 70)\nfor tc in test_cases:\n    print(f\"\\nSCENARIO: {tc['desc']}\")\n    prompt = build_prompt(\"USR01\", tc[\"capital\"], tc[\"holdings\"], tc[\"obligation\"], test_bbos)\n    messages = [\n        {\"role\": \"system\", \"content\": SYSTEM_PROMPT},\n        {\"role\": \"user\",   \"content\": prompt},\n    ]\n    output = pipe(\n        messages,\n        max_new_tokens=60,\n        temperature=0.3,\n        do_sample=True,\n        pad_token_id=tokenizer.eos_token_id,\n    )\n    response = output[0][\"generated_text\"][-1][\"content\"].strip()\n    print(f\"RESPONSE: {response}\")\n    try:\n        m = re.search(r\"\\{[^}]+\\}\", response)\n        if m:\n            d = json.loads(m.group())\n            assert d[\"side\"] in (\"BUY\", \"SELL\")\n            assert d[\"symbol\"] in [s[\"symbol\"] for s in SECURITIES]\n            assert d[\"quantity\"] > 0\n            assert d[\"price\"] > 0\n            print(f\"✓ Valid JSON: {d}\")\n        else:\n            print(\"✗ No JSON found in response\")\n    except Exception as e:\n        print(f\"✗ Invalid: {e}\")\n    print(\"-\" * 70)",
+   "source": "import re\nfrom transformers import pipeline\nfrom peft import PeftModel\n\n# Load adapter for inference test\nprint(\"Loading base model + adapter for inference test...\")\ndel trainer\ntorch.cuda.empty_cache()\n\nbase_model = AutoModelForCausalLM.from_pretrained(\n    BASE_MODEL,\n    quantization_config=BitsAndBytesConfig(\n        load_in_4bit=True,\n        bnb_4bit_quant_type=\"nf4\",\n        bnb_4bit_compute_dtype=torch.bfloat16,\n        bnb_4bit_use_double_quant=True,\n    ),\n    device_map=\"auto\",\n    trust_remote_code=True,\n)\ninference_model = PeftModel.from_pretrained(base_model, OUTPUT_DIR)\ninference_model.eval()\n\npipe = pipeline(\n    \"text-generation\",\n    model=inference_model,\n    tokenizer=tokenizer,\n    device_map=\"auto\",\n)\n\ntest_cases = [\n    {\n        \"desc\": \"New member, no holdings, must trade\",\n        \"capital\": 100_000.0,\n        \"holdings\": [],\n        \"obligation\": 10,\n    },\n    {\n        \"desc\": \"Experienced member with holdings, low obligation\",\n        \"capital\": 65_000.0,\n        \"holdings\": [\n            {\"symbol\": \"ALPHA\", \"quantity\": 300, \"avg_cost\": 5.60},\n            {\"symbol\": \"QUEST\", \"quantity\": 150, \"avg_cost\": 13.20},\n        ],\n        \"obligation\": 2,\n    },\n    {\n        \"desc\": \"Low capital, large holdings\",\n        \"capital\": 8_000.0,\n        \"holdings\": [\n            {\"symbol\": \"PEIR\",  \"quantity\": 500, \"avg_cost\": 8.30},\n            {\"symbol\": \"NBG\",   \"quantity\": 200, \"avg_cost\": 7.95},\n        ],\n        \"obligation\": 5,\n    },\n]\n\ntest_bbos = {s[\"symbol\"]: gen_bbo(s[\"base\"]) for s in SECURITIES}\n\nprint(\"=\" * 70)\nfor tc in test_cases:\n    print(f\"\\nSCENARIO: {tc['desc']}\")\n    prompt = build_prompt(\"USR01\", tc[\"capital\"], tc[\"holdings\"], tc[\"obligation\"], test_bbos)\n    messages = [\n        {\"role\": \"system\", \"content\": SYSTEM_PROMPT},\n        {\"role\": \"user\",   \"content\": prompt},\n    ]\n    output = pipe(\n        messages,\n        max_new_tokens=60,\n        temperature=0.3,\n        do_sample=True,\n        pad_token_id=tokenizer.eos_token_id,\n    )\n    response = output[0][\"generated_text\"][-1][\"content\"].strip()\n    print(f\"RESPONSE: {response}\")\n    try:\n        m = re.search(r\"\\{[^}]+\\}\", response)\n        if m:\n            d = json.loads(m.group())\n            assert d[\"side\"] in (\"BUY\", \"SELL\")\n            assert d[\"symbol\"] in [s[\"symbol\"] for s in SECURITIES]\n            assert d[\"quantity\"] > 0\n            assert d[\"price\"] > 0\n            print(f\"Valid JSON: {d}\")\n        else:\n            print(\"No JSON found in response\")\n    except Exception as e:\n        print(f\"Invalid: {e}\")\n    print(\"-\" * 70)",
    "metadata": {
     "id": "inference-test",
     "trusted": true