commit 40bc29de141647fc86b669713aaee08c624eea32 Author: ModelHub XC Date: Fri Aug 28 16:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Ayansk11/FinSenti-DeepSeek-R1-1.5B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e913005 --- /dev/null +++ b/README.md @@ -0,0 +1,226 @@ +--- +license: apache-2.0 +language: + - en +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B +datasets: + - Ayansk11/FinSenti-Dataset +pipeline_tag: text-generation +library_name: transformers +tags: + - finance + - financial-sentiment + - sentiment-analysis + - chain-of-thought + - reasoning + - grpo + - sft + - lora + - finsenti +--- +# FinSenti-DeepSeek-R1-1.5B + +FinSenti-DeepSeek-R1-1.5B is a 1.5B-parameter model fine-tuned to +read short financial text (headlines, earnings snippets, market commentary) +and explain its read of them before settling on positive, negative, or +neutral. It's built on DeepSeek's R1 distillation, so it already had a decent reasoning prior coming in. The SFT + GRPO passes narrow that reasoning to financial sentiment specifically. + +The model is part of the [FinSenti +collection](https://huggingface.co/collections/Ayansk11/finsenti), a +scaling study of small models trained on the same data with the same recipe. + +## What it's good at + +- Classifying short financial text (1-3 sentences) into positive / negative + / neutral +- Producing a short reasoning chain you can read or log +- Following a strict `......` output + format that's easy to parse downstream + +It was trained on news-style headlines and earnings snippets in English, so +that's where it shines. Outside that domain you'll see the format hold up +but the labels get noisier. + +## How it was trained + +Two-stage recipe, same across the whole FinSenti family: + +1. **SFT** on the SFT train slice from the [FinSenti + dataset](https://huggingface.co/datasets/Ayansk11/FinSenti-Dataset) + (~15.2K balanced training samples, drawn from a + 50.8K-sample pool with held-out val/test splits, chain-of-thought + targets generated by a teacher model and filtered for label agreement). + This stage took about 0.6 hours on a single A100 80GB + for this model. +2. **GRPO** with four reward functions (sentiment correctness, format + compliance, reasoning quality, output consistency), each weighted equally + for a maximum reward of 4.0. The training budget was 3000 + steps with early stopping; the best checkpoint landed near step + ~360 with a mean reward of approximately + **3.13 / 4.0** on the validation slice. + +Trainer stack: Unsloth + TRL, using Unsloth's pre-quantized mirror +[`unsloth/DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B) as the +loading shortcut for the upstream +[`deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) +weights. LoRA adapters (r=32, alpha=64) were +trained on the attention and MLP projection layers, then merged into the +base weights before export, so this repo is a self-contained model and +doesn't need PEFT to load. + +## Quick start + +Standard `transformers` usage: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "Ayansk11/FinSenti-DeepSeek-R1-1.5B" +tok = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, torch_dtype=torch.bfloat16, device_map="auto" +) + +system = ( + "You are a financial sentiment analyst. For each headline you receive, " + "write a short reasoning chain inside ... tags, " + "then give a single label inside ... tags. The label " + "must be exactly one of: positive, negative, neutral." +) +user = "Apple beats Q4 estimates as iPhone sales jump 12% year over year." + +messages = [ + {"role": "system", "content": system}, + {"role": "user", "content": user}, +] +prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) + +inputs = tok(prompt, return_tensors="pt").to(model.device) +out = model.generate(**inputs, max_new_tokens=256, do_sample=False) +print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)) +``` + +Expected output (your reasoning text will vary; the label should match): + +``` + +Beating estimates is a positive earnings surprise. A 12% YoY iPhone sales jump in the company's biggest product line points to demand strength. Both signals push the read positive. + +positive +``` + +## Prompt format + +The model expects the system prompt above, verbatim is best. The user turn +is the headline or short snippet you want classified. Output is two XML-ish +blocks in this order: `...` then +`...`. The `` content is one of `positive`, +`negative`, or `neutral` (lowercase, no punctuation). + +If you want labels only and don't care about the reasoning, you can stop +generation as soon as you see `` to save tokens. + +## Performance notes + +The training reward (max 4.0) hit **3.13** on the +held-out validation slice. That breaks down across the four reward +functions roughly as: + +- Sentiment correctness: dominant contributor; the model gets the label + right on the validation split most of the time +- Format compliance: near-saturated by the end of GRPO; the model almost + always produces well-formed `` and `` tags +- Reasoning quality: judged on length and presence of finance-relevant + signal words; this one's the noisiest of the four +- Consistency: rewards stable labels across paraphrases of the same headline + +Numbers on standard finance benchmarks (FPB, FiQA, Twitter Financial News) +are forthcoming and will be added once the eval pipeline lands. + +## Hardware + +bf16 weights are about 3.0 GB. You want ~4 GB of VRAM for batch=1 inference. CPU works but is slower; the Q4_K_M GGUF is the right pick if you don't have a GPU. + +## Limitations + +A few things this model isn't built for: + +- **Long documents.** Training context was capped at 2048 + tokens. Anything much longer than a few paragraphs is out of distribution. +- **Multi-asset reasoning.** It classifies the sentiment of a single piece + of text. It won't aggregate across multiple headlines or weigh sources. +- **Numerical reasoning.** It can read "beats by 12%" and call that + positive, but it isn't doing math. Don't ask it to forecast. +- **Languages other than English.** Training data was English only. +- **Background knowledge.** If the headline needs you to know what a + company does, the model only has whatever was in its base pretraining. + It can't look anything up. +- **Three labels, hard cutoffs.** The output space is positive / negative / + neutral. If you need a 5-class scale or a continuous score, you'll need + to retrain or post-process. + +## Training details + +| | | +|---|---| +| Upstream base model | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | +| Loading mirror | [unsloth/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B) (Unsloth's pre-quantized copy) | +| Dataset | [Ayansk11/FinSenti-Dataset](https://huggingface.co/datasets/Ayansk11/FinSenti-Dataset) (~15.2K train per stage, 50.8K total across splits) | +| SFT length | ~0.6 hours on A100 80GB | +| GRPO budget | 3000 steps with early stopping (best near step ~360) | +| Best GRPO reward | ~3.13 / 4.0 | +| Adapter | LoRA (r=32, alpha=64) on q/k/v/o/gate/up/down projections | +| Sequence length | 2048 | +| Optimizer | AdamW (8-bit), cosine LR schedule | +| Hardware | NVIDIA A100 80GB (Indiana University BigRed200 cluster) | +| Frameworks | Unsloth + TRL | + +## Related FinSenti models + +Other sizes and bases trained with the same recipe: + +- **Qwen3**: [Qwen3-0.6B](https://huggingface.co/Ayansk11/FinSenti-Qwen3-0.6B), [Qwen3-1.7B](https://huggingface.co/Ayansk11/FinSenti-Qwen3-1.7B), [Qwen3-4B](https://huggingface.co/Ayansk11/FinSenti-Qwen3-4B), [Qwen3-8B](https://huggingface.co/Ayansk11/FinSenti-Qwen3-8B) +- **Qwen3.5**: [Qwen3.5-0.8B](https://huggingface.co/Ayansk11/FinSenti-Qwen3.5-0.8B), [Qwen3.5-2B](https://huggingface.co/Ayansk11/FinSenti-Qwen3.5-2B), [Qwen3.5-4B](https://huggingface.co/Ayansk11/FinSenti-Qwen3.5-4B), [Qwen3.5-9B](https://huggingface.co/Ayansk11/FinSenti-Qwen3.5-9B) +- **MobileLLM**: [MobileLLM-R1-950M](https://huggingface.co/Ayansk11/FinSenti-MobileLLM-R1-950M) +- **Tiny-LLM**: [Tiny-LLM-10M](https://huggingface.co/Ayansk11/FinSenti-Tiny-LLM-10M) +- **Llama-3**: [Llama-3.2-1B](https://huggingface.co/Ayansk11/FinSenti-Llama-3.2-1B) +- **SmolLM**: [SmolLM-1.7B](https://huggingface.co/Ayansk11/FinSenti-SmolLM-1.7B) + +There's a GGUF build of this same model at +[Ayansk11/FinSenti-DeepSeek-R1-1.5B-GGUF](https://huggingface.co/Ayansk11/FinSenti-DeepSeek-R1-1.5B-GGUF) for Ollama and +llama.cpp, and the dataset itself is at +[Ayansk11/FinSenti-Dataset](https://huggingface.co/datasets/Ayansk11/FinSenti-Dataset). + +If you're picking a size, a rough guide: + +- **Need it on a phone or browser?** Look at the smallest model in the + group (Qwen3-0.6B) or its GGUF. +- **Laptop with no GPU?** Any model up to ~2B as Q4_K_M GGUF works. +- **Single 8-12 GB GPU?** The 1.5B-4B sizes are the sweet spot. +- **Server or workstation?** The 8B / 9B variants give the best reasoning + but need the memory. + +## Citation + +If you use this model in research, please cite: + +```bibtex +@misc{shaikh2026finsenti, + title = {FinSenti: Small Language Models for Financial Sentiment with Chain-of-Thought Reasoning}, + author = {Shaikh, Ayan}, + year = {2026}, + url = {https://huggingface.co/collections/Ayansk11/finsenti}, + note = {Indiana University} +} +``` + +## License + +Apache 2.0, same as the base model. + +## Acknowledgements + +Trained on the Indiana University BigRed200 cluster. +Thanks to the Unsloth and TRL teams for the trainer stack, and to the +Qwen / DeepSeek teams for the base models. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..cf43216 --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "torch_dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "unsloth_version": "2026.3.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d07ef27 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8dc0832b490c7aecf5cc3f594434c98048746f1fcf4cbe309efe01c618cae2a +size 3554214621 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cf6d5fc --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72d364a37413ca00a9000b2d2cff0be9c4511c6d1565263dcca665c5911c4ca +size 11422968 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d3c31a3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,18 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "from_slow": true, + "is_local": false, + "legacy": false, + "model_max_length": 131072, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "TokenizersBackend", + "unk_token": null, + "use_default_system_prompt": false, + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message.get('content') is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}" +} \ No newline at end of file