commit 019766e585f862b30e602987a4441b8ce097ef2d Author: ModelHub XC Date: Fri Jul 17 18:50:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: NOSIBLE/financial-sentiment-v1.2-base 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..78db773 --- /dev/null +++ b/README.md @@ -0,0 +1,327 @@ +--- +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE +pipeline_tag: text-generation +base_model: + - Qwen/Qwen3-0.6B-Base +tags: + - financial-sentiment + - finance + - sentiment-analysis + - nlp +--- + +

+ +

+ +## Changelog +- **v1.2.0:** Multilingual upgrade. Extends coverage to **94 languages** while holding English performance flat, and adds currency / G10-geography coverage. +- **v1.1.0:** English financial-sentiment model trained on real-world Nosible Search Feeds. + +**financial-sentiment-v1.2-base** is a financial sentiment classification model built to determine whether a short text snippet describes an event likely to have a **positive**, **neutral**, or **negative** financial impact. It is fine-tuned from [**Qwen3-0.6B-Base**](https://huggingface.co/Qwen/Qwen3-0.6B) and reframes sentiment classification as instruction following, producing a single label token per input. + +This is the **multilingual successor to [financial-sentiment-v1.1-base](https://huggingface.co/NOSIBLE/financial-sentiment-v1.1-base)**. v1.1 was trained primarily on English; v1.2 extends the same task to **94 languages** (English plus 93 additional languages) so the model can classify financial sentiment on text as it appears across global news and search feeds. + +### What's new in v1.2 + +- **Multilingual coverage.** The training corpus extends the English [Financial Sentiment](https://huggingface.co/datasets/NOSIBLE/financial-sentiment) data with faithful translations across 93 additional languages, where the financial-sentiment label is preserved through translation (a financially negative snippet stays negative, etc.). +- **Wider topic coverage.** v1.2 adds currency and G10-geography feeds, improving sentiment classification on currency- and country / region-focused text, not just company news. +- **English held flat.** v1.2 is a multilingual extension, not an English re-train. English accuracy and macro-F1 are unchanged within run noise (see below). +- **The multilingual gap roughly halved.** On the held-out validation set, the English-vs-multilingual accuracy gap shrinks from **~11.0pp** (v1.1) to **~4.8pp** (v1.2). + +### Performance overview + +All numbers below are measured on the **live SGLang endpoint** (OpenAI-compatible chat-completions, `enable_thinking=False`, `temperature=0`), scored against the same held-out validation splits for both models. Deltas are in **percentage points (pp)**. + +#### Headline + +| Slice | n | Metric | v1.1 | v1.2 | Δ | +|-------|---:|--------|-----:|-----:|----:| +| English val | 20,000 | Accuracy | 87.70% | 87.97% | +0.27pp | +| English val | 20,000 | Macro-F1 | 87.95% | 88.22% | +0.27pp | +| **Multilingual val** | 19,194 | Accuracy | 76.69% | **83.16%** | **+6.47pp** | +| **Multilingual val** | 19,194 | Macro-F1 | 76.90% | **83.27%** | **+6.37pp** | +| Currency / geo feeds | 4,012 | Accuracy | 67.30% | 76.17% | +8.87pp | +| Currency / geo feeds | 4,012 | Macro-F1 | 67.44% | 75.69% | +8.25pp | + +English is held flat while multilingual accuracy improves by **+6.47pp** and the currency / geography feeds improve by **+8.87pp**. + +#### Selected languages (largest validation slices) + +| Language | n | v1.1 acc | v1.2 acc | Δ acc | +|----------|---:|--------:|--------:|------:| +| German (de) | 1,597 | 82.22% | 87.16% | +4.94pp | +| Japanese (ja) | 1,508 | 80.17% | 85.08% | +4.91pp | +| Spanish (es) | 1,263 | 82.82% | 86.54% | +3.72pp | +| Russian (ru) | 1,686 | 83.75% | 86.89% | +3.14pp | +| French (fr) | 1,233 | 84.18% | 86.94% | +2.76pp | +| Portuguese (pt) | 730 | 82.60% | 85.07% | +2.47pp | +| Italian (it) | 673 | 85.14% | 87.37% | +2.23pp | +| Chinese (zh) | 1,383 | 84.24% | 86.12% | +1.88pp | +| Polish (pl) | 594 | 78.45% | 85.35% | +6.90pp | +| Dutch (nl) | 511 | 77.89% | 83.56% | +5.67pp | + +The gains are largest on lower-resource languages, where v1.1 tended to collapse to the dominant class. For example, accuracy rises on Tamil (40.35% → 73.68%), Hausa (39.39% → 65.66%), and Swahili (44.74% → 63.16%), with even larger macro-F1 improvements as the model recovers per-class signal. + +## Strict Usage Requirements + +> [!CAUTION] +> 1. **Disable Thinking:** You **must** set `enable_thinking=False` (or disable reasoning tokens). +> 2. **Exact System Prompt:** You **must** use the specific system prompt: `"Classify the financial sentiment as positive, neutral, or negative."` +> 3. **Constrain Output:** You **must** restrict generation to the valid labels (`["positive", "neutral", "negative"]`) using **grammars**, **regex**, or **guided decoding**. +> * **SGLang:** Use `regex="(positive|neutral|negative)"` in the API call. +> * **vLLM:** Use `guided_choice=["positive", "negative", "neutral"]` in the API call. +> * **llama.cpp / GGUF:** Apply a GBNF grammar or regex to force selection from the list. +> +> Deviating from these requirements will **severely** impact performance and reliability. + +## Quickstart (local GPU) + +Since this model was trained as a Causal LM using specific chat templates, you must use `apply_chat_template` with the exact system prompt used during training. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "NOSIBLE/financial-sentiment-v1.2-base" + +tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained( + model_id, + device_map="auto", + trust_remote_code=True, + torch_dtype=torch.bfloat16, +) + +# Multilingual input is supported (94 languages). +text = "La empresa reportó un margen de beneficio récord del 15% este trimestre." + +# 1. Structure the prompt exactly as used in training +messages = [ + {"role": "system", "content": "Classify the financial sentiment as positive, neutral, or negative."}, + {"role": "user", "content": text}, +] + +# 2. Apply chat template (thinking MUST be disabled) +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, + enable_thinking=False, +) + +inputs = tokenizer([prompt], return_tensors="pt").to(model.device) + +# 3. Generate the label (only a single token is expected) +outputs = model.generate(**inputs, max_new_tokens=1) +response = tokenizer.decode(outputs[0], skip_special_tokens=True) + +print(response.split("<|im_start|>assistant\n")[-1]) +# Expected Output: positive +``` + +## Deployment + +For production we recommend serving with [**SGLang**](https://github.com/sgl-project/sglang) (`sglang>=0.4.6.post1`), which exposes an OpenAI-compatible API endpoint. The model is based on Qwen3-0.6B and can be deployed anywhere Qwen3-0.6B can. + +**Launch the server:** + +```shell +python3 -m sglang.launch_server --model-path NOSIBLE/financial-sentiment-v1.2-base --dtype bfloat16 --host 0.0.0.0 --port 8080 +``` + +**Call the endpoint** using the OpenAI-compatible client. Requesting `logprobs` lets you read a calibrated confidence for each label. + +```python +import math +from openai import OpenAI + +# OpenAI-compatible client pointed at your SGLang server (set base_url to your +# endpoint URL if remote). The request shape mirrors signals_deploy_v12.predict_one. +client = OpenAI(base_url="http://localhost:8080/v1", api_key="EMPTY") + +model_id = "NOSIBLE/financial-sentiment-v1.2-base" + +# Multilingual input is supported. +text = "La empresa reportó un margen de beneficio récord del 15% este trimestre." + +messages = [ + {"role": "system", "content": "Classify the financial sentiment as positive, neutral, or negative."}, + {"role": "user", "content": text}, +] + +completion = client.chat.completions.create( + model=model_id, + messages=messages, + temperature=0, + stream=False, + logprobs=True, + top_logprobs=3, + extra_body={"chat_template_kwargs": {"enable_thinking": False}}, # Must be set to false. +) + +# The top-1 token is the predicted label; the full top_logprobs slice gives a +# per-label confidence. +top = completion.choices[0].logprobs.content[0].top_logprobs +print(f"Input: {text}") +print(f"Predicted Label: {top[0].token.strip()}") +print("--- Label Confidence ---") +for lp in top: + print(f"Token: {lp.token.strip()!r} | Probability: {math.exp(lp.logprob):.2%}") +``` + +#### Expected Output + +```text +Input: La empresa reportó un margen de beneficio récord del 15% este trimestre. +Predicted Label: positive + +--- Label Confidence --- +Token: 'positive' | Probability: 99.87% +Token: 'neutral' | Probability: 0.11% +Token: 'negative' | Probability: 0.02% +``` + +**Legal Notice:** This model is a modification of the Qwen3-0.6B model. In compliance with the Apache 2.0 license, we retain all original copyright notices and provide this modification under the same license terms. + +## Limitations + +* **Parameter Size (0.6B):** As a small language model, it is designed for fast, specific classification and may struggle with highly nuanced or ambiguous text that requires extensive world knowledge. +* **Per-language quality varies.** Accuracy on the highest-resource languages approaches the English baseline; lower-resource languages remain below it despite the large v1.2 improvements. +* **Domain Specificity:** The model is fine-tuned on **financial contexts**. It is not suitable for general sentiment analysis (e.g. product reviews). +* **Not aspect-based:** The model returns a single, blunt sentiment for the snippet as a whole. It does **not** perform aspect-based sentiment analysis — it will not attribute different sentiments to different entities, companies, or aspects mentioned in the same text. +* **Factuality:** The model analyzes the *sentiment* of the text provided; it does not verify the factual accuracy of any figures, dates, or claims within it. + +## Disclaimer + +* **Not Financial Advice:** The outputs of this model **should not be interpreted as financial advice, investment recommendations, or an endorsement** of any financial instrument or asset. +* **Risk:** Financial markets are inherently volatile and risky. **Never make investment decisions based solely on the output of an AI model.** Always consult with a qualified financial professional. + +## Team & Credits + +This model was developed and maintained by the following team: + +* [**Matthew Dicks**](https://www.linkedin.com/in/matthewdicks98/) +* [**Gareth Warburton**](https://www.linkedin.com/in/garethwarburton/) +* [**Stuart Reid**](https://www.linkedin.com/in/stuartgordonreid/) + +## Citation + +If you use this model, please cite it as follows: + +```bibtex +@misc{nosible2025financialsentimentv12, + author = {NOSIBLE}, + title = {Financial Sentiment v1.2 Base}, + year = {2025}, + publisher = {Hugging Face}, + journal = {Hugging Face Repository}, + howpublished = {https://huggingface.co/NOSIBLE/financial-sentiment-v1.2-base} +} +``` + + +## Full language breakdown + +v1.1 was trained on **English only**; v1.2 adds the **93 languages** below (94 total +with English). The figures are the training-time evaluation per language and reproduce +on the served SGLang endpoint to within ~0.2pp. Deltas are in percentage points (pp), +sorted by validation row count. + +| Language | n | v1.1 acc | v1.2 acc | Δ acc | v1.1 F1 | v1.2 F1 | Δ F1 | +|----------|---:|--------:|--------:|------:|-------:|-------:|------:| +| Russian (ru) | 1,686 | 83.63% | 86.83% | +3.20pp | 83.91% | 86.88% | +2.97pp | +| German (de) | 1,597 | 82.15% | 87.16% | +5.01pp | 82.25% | 87.50% | +5.25pp | +| Japanese (ja) | 1,507 | 80.36% | 85.14% | +4.78pp | 80.50% | 85.59% | +5.09pp | +| Chinese (zh) | 1,382 | 84.30% | 86.25% | +1.95pp | 84.59% | 86.49% | +1.90pp | +| Spanish (es) | 1,263 | 82.90% | 86.38% | +3.48pp | 82.91% | 86.57% | +3.66pp | +| French (fr) | 1,233 | 84.02% | 86.86% | +2.84pp | 84.81% | 87.55% | +2.74pp | +| Portuguese (pt) | 730 | 82.60% | 85.21% | +2.61pp | 82.96% | 85.58% | +2.62pp | +| Italian (it) | 673 | 85.44% | 87.37% | +1.93pp | 85.54% | 87.75% | +2.21pp | +| Polish (pl) | 594 | 78.45% | 85.52% | +7.07pp | 78.61% | 85.37% | +6.76pp | +| Dutch (nl) | 511 | 78.28% | 83.76% | +5.48pp | 79.13% | 84.28% | +5.15pp | +| Turkish (tr) | 393 | 79.13% | 81.93% | +2.80pp | 78.78% | 81.71% | +2.93pp | +| Indonesian (id) | 383 | 80.94% | 86.42% | +5.48pp | 80.99% | 86.62% | +5.63pp | +| Vietnamese (vi) | 366 | 83.06% | 82.51% | -0.55pp | 83.82% | 82.83% | -0.99pp | +| Czech (cs) | 331 | 78.55% | 84.59% | +6.04pp | 78.62% | 84.18% | +5.56pp | +| Korean (ko) | 291 | 80.41% | 84.54% | +4.13pp | 81.46% | 85.04% | +3.58pp | +| Arabic (ar) | 288 | 78.82% | 82.29% | +3.47pp | 77.98% | 82.15% | +4.17pp | +| Ukrainian (uk) | 247 | 79.76% | 84.21% | +4.45pp | 80.32% | 84.52% | +4.20pp | +| Swedish (sv) | 228 | 81.14% | 84.65% | +3.51pp | 80.61% | 84.71% | +4.10pp | +| Romanian (ro) | 227 | 78.85% | 84.58% | +5.73pp | 79.82% | 85.19% | +5.37pp | +| Hindi (hi) | 190 | 68.42% | 80.53% | +12.11pp | 66.87% | 80.80% | +13.93pp | +| Greek (el) | 187 | 67.91% | 77.54% | +9.63pp | 64.64% | 76.79% | +12.15pp | +| Hungarian (hu) | 178 | 72.47% | 81.46% | +8.99pp | 72.05% | 81.06% | +9.01pp | +| Thai (th) | 178 | 75.84% | 87.64% | +11.80pp | 77.31% | 88.06% | +10.75pp | +| Danish (da) | 177 | 79.66% | 84.75% | +5.09pp | 78.53% | 83.92% | +5.39pp | +| Bengali (bn) | 145 | 62.07% | 75.86% | +13.79pp | 57.80% | 75.14% | +17.34pp | +| Slovak (sk) | 145 | 76.55% | 81.38% | +4.83pp | 75.76% | 81.08% | +5.32pp | +| Malay (ms) | 143 | 81.12% | 83.22% | +2.10pp | 81.49% | 83.97% | +2.48pp | +| Persian (fa) | 136 | 75.74% | 79.41% | +3.67pp | 74.98% | 79.14% | +4.16pp | +| Finnish (fi) | 136 | 64.71% | 79.41% | +14.70pp | 62.60% | 79.55% | +16.95pp | +| Urdu (ur) | 121 | 71.07% | 76.03% | +4.96pp | 68.50% | 73.49% | +4.99pp | +| Norwegian (no) | 115 | 76.52% | 82.61% | +6.09pp | 77.06% | 82.95% | +5.89pp | +| Swahili (sw) | 114 | 44.74% | 62.28% | +17.54pp | 28.99% | 61.13% | +32.14pp | +| Tamil (ta) | 114 | 40.35% | 73.68% | +33.33pp | 31.49% | 72.14% | +40.65pp | +| Serbian (sr) | 113 | 83.19% | 86.73% | +3.54pp | 83.84% | 87.42% | +3.58pp | +| Hebrew (he) | 110 | 77.27% | 82.73% | +5.46pp | 76.88% | 82.95% | +6.07pp | +| Marathi (mr) | 110 | 50.00% | 80.00% | +30.00pp | 48.89% | 79.98% | +31.09pp | +| Bulgarian (bg) | 108 | 84.26% | 87.96% | +3.70pp | 83.11% | 86.97% | +3.86pp | +| Punjabi (pa) | 107 | 55.14% | 75.70% | +20.56pp | 51.59% | 74.99% | +23.40pp | +| Telugu (te) | 103 | 42.72% | 80.58% | +37.86pp | 32.33% | 80.19% | +47.86pp | +| Hausa (ha) | 99 | 39.39% | 64.65% | +25.26pp | 25.76% | 63.19% | +37.43pp | +| Tagalog (tl) | 99 | 73.74% | 77.78% | +4.04pp | 72.53% | 77.42% | +4.89pp | +| Gujarati (gu) | 98 | 53.06% | 78.57% | +25.51pp | 46.11% | 75.81% | +29.70pp | +| Kannada (kn) | 92 | 51.09% | 72.83% | +21.74pp | 38.24% | 72.06% | +33.82pp | +| Croatian (hr) | 90 | 76.67% | 81.11% | +4.44pp | 73.00% | 80.94% | +7.94pp | +| Azerbaijani (az) | 88 | 69.32% | 75.00% | +5.68pp | 60.86% | 71.82% | +10.96pp | +| Pashto (ps) | 88 | 45.45% | 69.32% | +23.87pp | 34.32% | 68.89% | +34.57pp | +| Malayalam (ml) | 86 | 47.67% | 72.09% | +24.42pp | 38.68% | 72.09% | +33.41pp | +| Nepali (ne) | 84 | 64.29% | 76.19% | +11.90pp | 62.22% | 76.41% | +14.19pp | +| Uzbek (uz) | 84 | 54.76% | 73.81% | +19.05pp | 48.65% | 73.47% | +24.82pp | +| Burmese (my) | 83 | 48.19% | 69.88% | +21.69pp | 36.83% | 70.75% | +33.92pp | +| Odia (or) | 82 | 43.90% | 69.51% | +25.61pp | 32.05% | 68.73% | +36.68pp | +| Amharic (am) | 77 | 42.86% | 66.23% | +23.37pp | 23.46% | 59.46% | +36.00pp | +| Kazakh (kk) | 77 | 57.14% | 79.22% | +22.08pp | 50.37% | 78.74% | +28.37pp | +| Somali (so) | 77 | 53.25% | 51.95% | -1.30pp | 33.35% | 50.88% | +17.53pp | +| Sindhi (sd) | 75 | 65.33% | 69.33% | +4.00pp | 63.63% | 67.47% | +3.84pp | +| Lithuanian (lt) | 73 | 63.01% | 71.23% | +8.22pp | 58.04% | 69.78% | +11.74pp | +| Sinhala (si) | 69 | 40.58% | 52.17% | +11.59pp | 23.58% | 45.35% | +21.77pp | +| Assamese (as) | 66 | 57.58% | 80.30% | +22.72pp | 54.79% | 79.92% | +25.13pp | +| Khmer (km) | 66 | 63.64% | 69.70% | +6.06pp | 57.87% | 67.45% | +9.58pp | +| Slovenian (sl) | 66 | 69.70% | 77.27% | +7.57pp | 63.82% | 73.55% | +9.73pp | +| Afrikaans (af) | 64 | 73.44% | 84.38% | +10.94pp | 73.38% | 84.64% | +11.26pp | +| Armenian (hy) | 56 | 57.14% | 67.86% | +10.72pp | 51.87% | 66.44% | +14.57pp | +| Kyrgyz (ky) | 48 | 43.75% | 77.08% | +33.33pp | 39.29% | 77.76% | +38.47pp | +| Latvian (lv) | 48 | 62.50% | 75.00% | +12.50pp | 56.46% | 74.84% | +18.38pp | +| Mongolian (mn) | 46 | 47.83% | 78.26% | +30.43pp | 31.94% | 75.92% | +43.98pp | +| Lao (lo) | 44 | 68.18% | 70.45% | +2.27pp | 68.80% | 68.63% | -0.17pp | +| Georgian (ka) | 41 | 41.46% | 75.61% | +34.15pp | 37.59% | 71.54% | +33.95pp | +| Sanskrit (sa) | 22 | 68.18% | 81.82% | +13.64pp | 65.56% | 78.89% | +13.33pp | +| Catalan (ca) | 21 | 61.90% | 85.71% | +23.81pp | 63.83% | 86.25% | +22.42pp | +| Bosnian (bs) | 20 | 75.00% | 85.00% | +10.00pp | 74.64% | 83.87% | +9.23pp | +| Irish (ga) | 20 | 35.00% | 55.00% | +20.00pp | 17.28% | 54.43% | +37.15pp | +| Malagasy (mg) | 20 | 50.00% | 75.00% | +25.00pp | 29.76% | 73.26% | +43.50pp | +| Welsh (cy) | 19 | 36.84% | 78.95% | +42.11pp | 23.33% | 76.67% | +53.34pp | +| Macedonian (mk) | 19 | 89.47% | 89.47% | +0.00pp | 91.07% | 91.07% | +0.00pp | +| Belarusian (be) | 18 | 61.11% | 72.22% | +11.11pp | 54.56% | 64.59% | +10.03pp | +| Basque (eu) | 18 | 33.33% | 72.22% | +38.89pp | 16.67% | 71.39% | +54.72pp | +| Latin (la) | 18 | 55.56% | 88.89% | +33.33pp | 37.78% | 81.75% | +43.97pp | +| Serbo-Croatian (sh) | 18 | 83.33% | 88.89% | +5.56pp | 82.44% | 88.97% | +6.53pp | +| Yiddish (yi) | 18 | 44.44% | 33.33% | -11.11pp | 20.51% | 42.91% | +22.40pp | +| Scottish Gaelic (gd) | 17 | 52.94% | 58.82% | +5.88pp | 23.08% | 55.58% | +32.50pp | +| Galician (gl) | 17 | 82.35% | 88.24% | +5.89pp | 81.10% | 84.72% | +3.62pp | +| Icelandic (is) | 17 | 47.06% | 64.71% | +17.65pp | 34.21% | 47.22% | +13.01pp | +| Oromo (om) | 17 | 41.18% | 58.82% | +17.64pp | 19.44% | 53.53% | +34.09pp | +| Xhosa (xh) | 17 | 35.29% | 47.06% | +11.77pp | 17.39% | 33.33% | +15.94pp | +| Breton (br) | 16 | 37.50% | 68.75% | +31.25pp | 35.56% | 70.56% | +35.00pp | +| Estonian (et) | 16 | 68.75% | 62.50% | -6.25pp | 67.97% | 63.57% | -4.40pp | +| Western Frisian (fy) | 16 | 68.75% | 62.50% | -6.25pp | 68.81% | 62.63% | -6.18pp | +| Javanese (jv) | 16 | 81.25% | 87.50% | +6.25pp | 77.46% | 82.37% | +4.91pp | +| Kurdish (ku) | 16 | 68.75% | 75.00% | +6.25pp | 47.62% | 82.14% | +34.52pp | +| Albanian (sq) | 16 | 68.75% | 81.25% | +12.50pp | 60.00% | 80.94% | +20.94pp | +| Sundanese (su) | 16 | 68.75% | 68.75% | +0.00pp | 71.31% | 72.03% | +0.72pp | +| Uyghur (ug) | 16 | 50.00% | 68.75% | +18.75pp | 22.22% | 48.81% | +26.59pp | +| Esperanto (eo) | 15 | 93.33% | 66.67% | -26.66pp | 91.58% | 67.74% | -23.84pp | diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..de74ee0 --- /dev/null +++ b/config.json @@ -0,0 +1,65 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.6.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936, + "rope_theta": 1000000, + "rope_scaling": null +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f892ceb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "bos_token_id": 151643, + "do_sample": false, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "transformers_version": "5.6.0" +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..602c723 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b810ddec66587a77fbd820dbd30d199b866841ab3b73b73b1ef6a00cc2493e +size 1192135096 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..23acf42 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,242 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "add_bos_token": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_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|>" + ] +} \ No newline at end of file