uploaded readme

README.md

@@ -0,0 +1,160 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+nekomata-14b-pfn-qfin - GGUF
+- Model creator: https://huggingface.co/pfnet/
+- Original model: https://huggingface.co/pfnet/nekomata-14b-pfn-qfin/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [nekomata-14b-pfn-qfin.Q2_K.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q2_K.gguf) | Q2_K | 5.41GB |
+| [nekomata-14b-pfn-qfin.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.IQ3_XS.gguf) | IQ3_XS | 6.12GB |
+| [nekomata-14b-pfn-qfin.IQ3_S.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.IQ3_S.gguf) | IQ3_S | 6.31GB |
+| [nekomata-14b-pfn-qfin.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q3_K_S.gguf) | Q3_K_S | 6.31GB |
+| [nekomata-14b-pfn-qfin.IQ3_M.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.IQ3_M.gguf) | IQ3_M | 6.87GB |
+| [nekomata-14b-pfn-qfin.Q3_K.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q3_K.gguf) | Q3_K | 7.16GB |
+| [nekomata-14b-pfn-qfin.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q3_K_M.gguf) | Q3_K_M | 7.16GB |
+| [nekomata-14b-pfn-qfin.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q3_K_L.gguf) | Q3_K_L | 7.44GB |
+| [nekomata-14b-pfn-qfin.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.IQ4_XS.gguf) | IQ4_XS | 7.37GB |
+| [nekomata-14b-pfn-qfin.Q4_0.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q4_0.gguf) | Q4_0 | 7.62GB |
+| [nekomata-14b-pfn-qfin.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.IQ4_NL.gguf) | IQ4_NL | 7.68GB |
+| [nekomata-14b-pfn-qfin.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q4_K_S.gguf) | Q4_K_S | 7.96GB |
+| [nekomata-14b-pfn-qfin.Q4_K.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q4_K.gguf) | Q4_K | 8.8GB |
+| [nekomata-14b-pfn-qfin.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q4_K_M.gguf) | Q4_K_M | 8.8GB |
+| [nekomata-14b-pfn-qfin.Q4_1.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q4_1.gguf) | Q4_1 | 8.4GB |
+| [nekomata-14b-pfn-qfin.Q5_0.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q5_0.gguf) | Q5_0 | 9.18GB |
+| [nekomata-14b-pfn-qfin.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q5_K_S.gguf) | Q5_K_S | 9.34GB |
+| [nekomata-14b-pfn-qfin.Q5_K.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q5_K.gguf) | Q5_K | 10.14GB |
+| [nekomata-14b-pfn-qfin.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q5_K_M.gguf) | Q5_K_M | 10.14GB |
+| [nekomata-14b-pfn-qfin.Q5_1.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q5_1.gguf) | Q5_1 | 9.96GB |
+| [nekomata-14b-pfn-qfin.Q6_K.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q6_K.gguf) | Q6_K | 11.46GB |
+| [nekomata-14b-pfn-qfin.Q8_0.gguf](https://huggingface.co/RichardErkhov/pfnet_-_nekomata-14b-pfn-qfin-gguf/blob/main/nekomata-14b-pfn-qfin.Q8_0.gguf) | Q8_0 | 14.03GB |
+
+
+
+
+Original model description:
+---
+license: other
+license_name: tongyi-qianwen-license
+license_link: LICENSE
+language:
+- en
+- ja
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# nekomata-14b-pfn-qfin
+
+## Model Description
+nekomata-14b-pfn-qfin is a fine-tuned model based on [rinna/nekomata-14b](https://huggingface.co/rinna/nekomata-14b/tree/main).
+This is the base model, which is good at generating continuous sentences for finance.
+nekomata-14b-pfn-qfin is fine-tuned on 370M tokens from multiple special datasets generated by Preferred Networks, which is clear to use for commercial usage.
+The fine-tuned were carried out at a 2048 context length.
+This model is released under [Tongyi Qianwen LICENSE AGREEMENT](https://github.com/QwenLM/Qwen/blob/e8e15962d897714944773cca57fa2e460a3655e8/Tongyi%20Qianwen%20LICENSE%20AGREEMENT).
+
+The research article is available on [arXiv](https://arxiv.org/abs/2404.10555).
+
+# Benchmarking
+The benchmark score is obtained using [Japanese Language Model Financial Evaluation Harness](https://github.com/pfnet-research/japanese-lm-fin-harness)
+For the benchmark, 0-shot and default prompts are used.
+```
+|      Task      |Metric|  nekomaba-14b   |       Ours      |
+|----------------|------|------|---|------|------|---|------|
+|chabsa          |f1    |0.7381|   |      |0.7428|   |      |
+|cma_basics      |acc   |0.4737|±  |0.0821|0.5263|±  |0.0821|
+|cpa_audit       |acc   |0.1608|±  |0.0184|0.1633|±  |0.0186|
+|fp2             |acc   |0.3389|±  |0.0217|0.3642|±  |0.0221|
+|security_sales_1|acc   |0.4561|±  |0.0666|0.5614|±  |0.0663|
+|----------------|------|------|---|------|------|---|------|
+|OVER ALL        |      |0.4335           |0.4716           |
+```
+## Usage
+Install the required libraries as follows:
+```sh
+>>> python -m pip install numpy sentencepiece torch transformers accelerate transformers_stream_generator tiktoken einops
+```
+
+Execute the following python code:
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("pfnet/nekomata-14b-pfn-qfin", trust_remote_code=True)
+
+# Use GPU with bf16 (recommended for supported devices)
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True, bf16=True)
+
+# Use GPU with fp16
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True, fp16=True)
+
+# Use GPU with fp32
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True, fp32=True)
+
+# Use CPU
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="cpu", trust_remote_code=True)
+
+# Automatically select device and precision
+model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True)
+
+text = "日本銀行は"
+input_ids = tokenizer(text, return_tensors="pt").input_ids.to(model.device)
+with torch.no_grad():
+  generated_tokens = model.generate(
+      inputs=input_ids,
+      max_new_tokens=32,
+      do_sample=True,
+      temperature=1.0,
+      repetition_penalty=1.1
+  )[0]
+generated_text = tokenizer.decode(generated_tokens)
+print(generated_text)
+# 日本銀行は、2016年9月に「長短金利操作付き量的・質的金融緩和」を導入し、長期国
+```
+
+## Model Details
+- Model size: 14B
+- Fine-tuned tokens: 370M tokens (Japanese: 300M tokens, English: 13M tokens, Digits: 14M tokens)
+- Context length: 2048
+- Developed by: Preferred Networks, Inc
+- Model type: Causal decoder-only
+- Language(s): Japanese and English
+- License: [Tongyi Qianwen LICENSE AGREEMENT](https://github.com/QwenLM/Qwen/blob/e8e15962d897714944773cca57fa2e460a3655e8/Tongyi%20Qianwen%20LICENSE%20AGREEMENT)
+
+## Bias, Risks, and Limitations
+nekomata-14b-pfn-qfin is a new technology that carries risks with use.
+Testing conducted to date has been in English and Japanese, and has not covered, nor could it cover all scenarios.
+For these reasons, as with all LLMs, nekomata-14b-pfn-qfin’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
+This model is not designed for legal, tax, investment, financial, or other advice.
+Therefore, before deploying any applications of nekomata-14b-pfn-qfin, developers should perform safety testing and tuning tailored to their specific applications of the model.
+
+## How to cite
+```
+@misc{hirano2024,
+      title={Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training}, 
+      author={Masanori Hirano and Kentaro Imajo},
+      year={2024},
+      eprint={2404.10555},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+## Contributors
+Preferred Networks, Inc.
+ - Masanori Hirano
+ - Kentaro Imajo
+
+# License
+[Tongyi Qianwen LICENSE AGREEMENT](https://github.com/QwenLM/Qwen/blob/e8e15962d897714944773cca57fa2e460a3655e8/Tongyi%20Qianwen%20LICENSE%20AGREEMENT)
+
+
+