Initial upload of SmolNewsAnalysis-002

MODEL_CARD.md

@@ -0,0 +1,99 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+pipeline_tag: text-generation
+model-index:
+- name: SmolNewsAnalysis-002
+  results:
+  - task:
+      type: text-generation
+      name: Financial news JSON scoring
+    metrics:
+    - name: Train loss
+      type: loss
+      value: 0.0925
+---
+
+# SmolNewsAnalysis-002 — SmolLM2-360M Financial News JSON Analyst
+
+## Model Details
+- **Developer** [Levi De Haan](https://levidehaan.com/)
+- **Base model** `HuggingFaceTB/SmolLM2-360M-Instruct` (360M parameter decoder-only transformer).
+- **Architecture** SmolLM-compatible causal language model with `<|im_start|>` chat formatting.
+- **Fine-tuning method** LoRA adapters (rank 8, alpha 16, dropout 0) trained with LLaMA-Factory and merged into the base weights.
+- **License** Apache-2.0 (inherits the base model license). No additional restrictions are applied.
+
+## Intended Use
+- **Primary objective** Convert financial news headlines and summaries into a compact JSON object containing `symbol`, `site`, `source_name`, `sentiment_score`, `sentiment_confidence`, `wow_score`, and `wow_confidence` for ingestion by the Twatter news pipeline (`src/stock_news_processor.py`).
+- **Input scope** Short- to mid-length finance news briefs gathered from Alpaca/FMP feeds or similar sources.
+- **Out-of-scope** General-purpose chat, long-form articles beyond the trimmed 1 800-character window, or non-financial domains.
+
+## Prompt Template
+- **System message** automatically injected by `chat_template.jinja` and the `Modelfile`:
+
+```text
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.
+```
+
+- **SmolLM chat framing**:
+
+```text
+<|im_start|>system
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.<|im_end|>
+<|im_start|>user
+<news article title/summary + metadata>
+<|im_end|>
+<|im_start|>assistant
+```
+
+- **`[INST]` format** when `TRAINED_MODEL_TYPE="llama"` in `SharedLLMManager`:
+
+```text
+<s>[INST] <<SYS>>
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.
+<</SYS>>
+
+<news article title/summary + metadata> [/INST]
+```
+
+The model is optimized to emit a single JSON object; downstream parsing stops at the first closing brace.
+
+## Training Data
+- **Dataset** `training_data/news_data/stock_news_training.json` (1506 deduplicated instruction/response pairs) produced via `extract_stock_json_news_training.py`.
+- **Composition** finance news with ticker/site metadata and minified JSON labels.
+
+## Training Procedure
+- **Frameworks** LLaMA-Factory + PEFT (LoRA) on bf16 hardware.
+- **Key hyperparameters** `learning_rate=5e-5`, `per_device_train_batch_size=2`, `gradient_accumulation_steps=8`, `num_train_epochs=10`, `cutoff_len=2048`, `lora_r=8`, `lora_alpha=16`, `lora_dropout=0`, `lr_scheduler_type=cosine_with_restarts`, `max_grad_norm=1.0`, `warmup_steps=0`.
+- **Tokens seen** 8757824 (`num_input_tokens_seen` in `all_results.json`).
+- **Final train loss** 0.0925 (see `LLaMA-Factory/saves/SmolLM2-360M-Instruct/lora/financial_news_model_json/all_results.json`).
+
+
+## Limitations
+- **Domain** Focused on short-form financial news; additional preprocessing may be required for long articles.
+- **Ticker detection** Relies on upstream metadata—empty `symbol` fields indicate the source lacked a ticker.
+- **JSON validity** Typically robust, yet integrating systems should validate responses before use.
+- **Temporal awareness** Model knowledge reflects historical data snapshots and does not account for real-time events.
+
+## Usage Example
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "LeviDeHaan/SmolNewsAnalysis-002"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
+
+prompt = """<|im_start|>system\nYou are a precise financial news analyst...<|im_end|>\n"""
+prompt += "<|im_start|>user\nTesla shares climb after deliveries beat expectations. Symbol: TSLA Site: bloomberg.com\n<|im_end|>\n<|im_start|>assistant\n"
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=160, temperature=0.1)
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+## Contact
+- **Maintainer** [Levi De Haan](https://levidehaan.com/)
+- **Project page** https://levidehaan.com/projects/twatter
+- **Hugging Face discussions** https://huggingface.co/LeviDeHaan/SmolNewsAnalysis-002/discussions

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary."""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,97 @@
+# SmolLM2-360M Financial News JSON Analyst (`SmolNewsAnalysis-002`)
+
+- **Hugging Face model card**: https://huggingface.co/LeviDeHaan/SmolNewsAnalysis-002
+- **Author**: [Levi De Haan](https://levidehaan.com/)
+- **Project overview**: https://levidehaan.com/projects/twatter
+
+## Overview
+- **Purpose** Fine-tuned SmolLM2-360M-Instruct to summarize Alpaca/FMP financial news into structured sentiment + significance scores consumed by the Twatter news pipeline.
+- **Base model** `HuggingFaceTB/SmolLM2-360M-Instruct` (360M parameters, Apache-2.0).
+- **Architecture** Decoder-only transformer compatible with SmolLM chat formatting (`...`).
+- **Finetuning method** LoRA adapters (rank 8, alpha 16, dropout 0) merged into base weights post-training.
+- **Repository integration** Loaded via `SharedLLMManager.TrainedModelClient` and invoked by `stock_news_processor.py` for Alpaca feed scoring.
+
+## What it Predicts
+- **sentiment_score** Float in `[-1, 1]` summarizing bullish/bearish tone.
+- **sentiment_confidence** Model confidence for sentiment score (float `0-1`).
+- **wow_score** Market impact category normalized to `Extremely Bad News`, `Bad News`, `Meh News`, `Regular News`, `Big News`, or `Huge News`.
+- **wow_confidence** Confidence for wow_score (float `0-1`).
+- **symbol** Canonical ticker symbol extracted from the article payload (may be empty if missing upstream).
+- **site / source_name** Strings describing origin; pass-through of Alpaca metadata for downstream routing.
+
+## Prompt Format
+- **System message** Injected automatically by `chat_template.jinja` and `Modelfile` when missing:
+
+```text
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.
+```
+
+- **Full chat template** used for SmolLM-style prompts:
+
+```text
+<|im_start|>system
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.<|im_end|>
+<|im_start|>user
+<news article title/summary + metadata>
+<|im_end|>
+<|im_start|>assistant
+
+```
+
+- **Alternative `[INST]` framing** used in `SharedLLMManager.TrainedModelClient.generate()` when `TRAINED_MODEL_TYPE="llama"`:
+
+```text
+<s>[INST] <<SYS>>
+You are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.
+<</SYS>>
+
+<news article title/summary + metadata> [/INST]
+```
+
+**Output** Must be a single JSON object; downstream parsing stops at the first closing brace.
+
+## Quick Start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "LeviDeHaan/SmolNewsAnalysis-002"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
+
+prompt = """<|im_start|>system\nYou are a precise financial news analyst...<|im_end|>\n"""
+prompt += "<|im_start|>user\nTesla shares climb after deliveries beat expectations. Symbol: TSLA Site: bloomberg.com\n<|im_end|>\n<|im_start|>assistant\n"
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=160, temperature=0.1)
+response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+print(response)
+```
+
+## Training Data
+- **Source** Aggregated Alpaca/FMP news processed by `stock_news_processor.py` and exported through `extract_stock_json_news_training.py` to `training_data/news_data/stock_news_training.json`.
+- **Samples** 1 506 deduplicated instruction/response pairs (hash dedupe over title/summary + ticker + site).
+- **Wow distribution** `Big News` 645, `Regular News` 272, `Bad News` 253, `Huge News` 198, `Meh News` 120, `Extremely Bad News` 16 (plus 2 legacy `Bad News (negative but not catastrophic)` entries coerced to canonical values at inference time).
+- **Content** News titles, summaries, symbol/site metadata, and minified JSON outputs describing sentiment and impact.
+
+## Training Procedure
+- **Framework** LLaMA-Factory (SmolLM2 template) + PEFT LoRA on bf16 accelerators.
+- **Hyperparameters** `learning_rate=5e-5`, `per_device_train_batch_size=2`, `gradient_accumulation_steps=8`, `num_train_epochs=10`, `cutoff_len=2048`, `lora_r=8`, `lora_alpha=16`, `lora_dropout=0`, `lr_scheduler_type=cosine_with_restarts`, `max_grad_norm=1.0`, `warmup_steps=0`.
+- **Tokens seen** 8 757 824 (`num_input_tokens_seen` in `all_results.json`).
+- **Final train loss** 0.0925.
+- **Adapters** Merged into base weights before export; no LoRA files required at inference.
+
+## Known Limitations
+- **Domain specificity** Tuned on short news briefs; long-form articles may require additional summarization or truncation (`stock_news_processor.py` trims to 1800 chars).
+- **JSON adherence** Strong but still validate output to guard against malformed fields.
+- **Ticker coverage** Relies on upstream symbol detection; missing tickers yield blank `symbol` values.
+- **Wow taxonomy** Responses outside the canonical set default to `Regular News` via analyzer normalization.
+- **Market latency** Model reflects historical data only; no real-time awareness or price prediction.
+
+## License
+- **Model weights** Apache-2.0 (inherits from base model).
+
+## Contact & Support
+- **Maintainer** [Levi De Haan](https://levidehaan.com/)
+- **Project page** https://levidehaan.com/projects/twatter
+- **Hugging Face discussions** https://huggingface.co/LeviDeHaan/SmolNewsAnalysis-002/discussions

chat_template.jinja

@@ -0,0 +1,9 @@
+{% for message in messages %}
+{% if loop.first and messages[0]['role'] != 'system' %}
+{{ '<|im_start|>system\nYou are a precise financial news analyst. Read the news text and output a compact JSON with fields: symbol, site, source_name, sentiment_score, sentiment_confidence, wow_score, wow_confidence. Output only the JSON without commentary.<|im_end|>\n' }}
+{% endif %}
+{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}
+{% endfor %}
+{% if add_generation_prompt %}
+{{ '<|im_start|>assistant\n' }}
+{% endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee452849e070e7995d3f2d3318bb77cc21e2a637243c737641cd6015a204dd39
+size 723674912

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,156 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}