初始化项目，由ModelHub XC社区提供模型

Model: RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,54 @@
+*.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
+SambaLingo-Russian-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+SambaLingo-Russian-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,180 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+SambaLingo-Russian-Chat - GGUF
+- Model creator: https://huggingface.co/sambanovasystems/
+- Original model: https://huggingface.co/sambanovasystems/SambaLingo-Russian-Chat/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [SambaLingo-Russian-Chat.Q2_K.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q2_K.gguf) | Q2_K | 2.47GB |
+| [SambaLingo-Russian-Chat.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q3_K_S.gguf) | Q3_K_S | 2.87GB |
+| [SambaLingo-Russian-Chat.Q3_K.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q3_K.gguf) | Q3_K | 3.19GB |
+| [SambaLingo-Russian-Chat.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q3_K_M.gguf) | Q3_K_M | 3.19GB |
+| [SambaLingo-Russian-Chat.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q3_K_L.gguf) | Q3_K_L | 3.47GB |
+| [SambaLingo-Russian-Chat.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.IQ4_XS.gguf) | IQ4_XS | 3.53GB |
+| [SambaLingo-Russian-Chat.Q4_0.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q4_0.gguf) | Q4_0 | 3.7GB |
+| [SambaLingo-Russian-Chat.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.IQ4_NL.gguf) | IQ4_NL | 3.72GB |
+| [SambaLingo-Russian-Chat.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q4_K_S.gguf) | Q4_K_S | 3.73GB |
+| [SambaLingo-Russian-Chat.Q4_K.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q4_K.gguf) | Q4_K | 3.94GB |
+| [SambaLingo-Russian-Chat.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q4_K_M.gguf) | Q4_K_M | 3.94GB |
+| [SambaLingo-Russian-Chat.Q4_1.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q4_1.gguf) | Q4_1 | 4.09GB |
+| [SambaLingo-Russian-Chat.Q5_0.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q5_0.gguf) | Q5_0 | 4.48GB |
+| [SambaLingo-Russian-Chat.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q5_K_S.gguf) | Q5_K_S | 4.48GB |
+| [SambaLingo-Russian-Chat.Q5_K.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q5_K.gguf) | Q5_K | 4.6GB |
+| [SambaLingo-Russian-Chat.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q5_K_M.gguf) | Q5_K_M | 4.6GB |
+| [SambaLingo-Russian-Chat.Q5_1.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q5_1.gguf) | Q5_1 | 4.87GB |
+| [SambaLingo-Russian-Chat.Q6_K.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q6_K.gguf) | Q6_K | 5.31GB |
+| [SambaLingo-Russian-Chat.Q8_0.gguf](https://huggingface.co/RichardErkhov/sambanovasystems_-_SambaLingo-Russian-Chat-gguf/blob/main/SambaLingo-Russian-Chat.Q8_0.gguf) | Q8_0 | 6.88GB |
+
+
+
+
+Original model description:
+---
+license: llama2
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+- HuggingFaceH4/cai-conversation-harmless
+language:
+- ru
+- en
+---
+
+
+
+# SambaLingo-Russian-Chat
+
+<img src="SambaLingo_Logo.png" width="340" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+<!-- Provide a quick summary of what the model is/does. -->
+SambaLingo-Russian-Chat is a human aligned chat model trained in Russian and English. It is trained using direct preference optimization on top the base model [SambaLingo-Russian-Base](https://huggingface.co/sambanovasystems/SambaLingo-Russian-Base). The base model adapts [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) to Russian by training on 63 billion tokens from the Russian split of the [Cultura-X](https://huggingface.co/datasets/uonlp/CulturaX) dataset. Try this model at [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space).
+
+## Model Description
+<!-- Provide a longer summary of what this model is. -->
+
+- **Developed by:** [SambaNova Systems](https://sambanova.ai/)
+- **Model type:** Language Model
+- **Language(s):** Russian, English
+- **Finetuned from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+- **Try this model:** [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space)
+- **Paper:** [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829)
+- **Blog Post**: [sambalingo-open-source-language-experts](https://sambanova.ai/blog/sambalingo-open-source-language-experts)
+
+## Getting Started
+
+### Loading Model With Hugging Face
+Please make sure to set use_fast=False when loading the tokenizer.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/SambaLingo-Russian-Chat", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("sambanovasystems/SambaLingo-Russian-Chat", device_map="auto", torch_dtype="auto")
+```
+
+### Interacting With Model Pipeline
+Please make sure to set use_fast=False when loading the tokenizer.
+```python
+from transformers import pipeline
+pipe = pipeline("text-generation", model="sambanovasystems/SambaLingo-Russian-Chat", device_map="auto", use_fast=False)
+messages = [
+                {"role": "user", "content": {YOUR_QUESTION}},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt)[0]
+outputs = outputs["generated_text"]
+```
+
+### Suggested Inference Parameters
+- Temperature: 0.8
+- Repetition penalty: 1.0
+- Top-p: 0.9
+
+### Prompting Guidelines
+To prompt this model, please use the following chat template:
+```
+<|user|>\n{question}</s>\n<|assistant|>\n
+```
+
+### Example Prompts and Generations
+```
+<|user|>
+Завершите параграф: Родион Раскольников - главный персонаж романа "Преступление и наказание" Федора Достоевского. Его характер очень сложен и     эволюционирует на протяжении всей истории. Он обладает выдающимися умственными способностями и амбициями, но</s>
+<|assistant|>
+его внутренняя бор    ьба и моральные сомнения мешают ему действовать в соответствии со своими желаниями. Раскольников — бедный студент, который терпит финансовые трудности и чувствует себ    я бессильным изменить свою жизнь. Он приходит к теории, согласно которой некоторые люди имеют право совершать преступления ради достижения великих целей, и решает про    верить свою теорию, убив старуху-процентщицу. Однако его действия приводят к глубокому чувству вины и психологическому срыву, который заставляет его искать искупления     и искупления. На протяжении всего романа Раскольников проходит путь самопознания и личностного роста, осознавая важность сочувствия, сострадания и ответственности пе    ред другими. В конечном итоге он принимает на себя ответственность за свои действия и находит искупление через раскаяние и прощение.
+```
+
+## Training Details
+The alignment phase follows the recipe for [Zephyr-7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), and comprises two stages: supervised fine-tuning (SFT) and Direct Performance Optimization (DPO).
+
+The SFT phase was done on the [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset mixed with the Google translated version of the ultrachat_200k dataset. It was trained for one epoch with global batch size 512 and max sequence length 2048 tokens. We used a linear decay learning rate of 2e-5 and 10% warmup.
+
+The DPO phase was done on the [ultrafeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset and [cai-conversation-harmless](https://huggingface.co/datasets/HuggingFaceH4/cai-conversation-harmless) dataset, mixed with 10% of the data Google translated. It was trained with global batch size 32 and for three epochs. We used a linear decay learning rate of 5e-7, 10% warmup and β=0.1 as the regularization factor for DPO. 
+
+
+## Tokenizer Details
+We extended the vocabulary of the base llama model from 32,000 tokens to 57,000 tokens by adding up to 25,000 non-overlapping tokens from the new language.
+
+## Evaluation
+For evaluation results see our paper: [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829)
+
+## Uses
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+Use of this model is governed by the Meta’s [Llama 2 Community License Agreement](https://ai.meta.com/llama/license/). Please review and accept the license before downloading the model weights.
+
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+SambaLingo should NOT be used for:
+
+- Mission-critical applications
+- Applications that involve the safety of others
+- Making highly important decisions
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+Like all LLMs, SambaLingo has certain limitations:
+- Hallucination: Model may sometimes generate responses that contain plausible-sounding but factually incorrect or irrelevant information.
+- Code Switching: The model might unintentionally switch between languages or dialects within a single response, affecting the coherence and understandability of the output.
+- Repetition: The Model may produce repetitive phrases or sentences, leading to less engaging and informative responses.
+- Coding and Math: The model's performance in generating accurate code or solving complex mathematical problems may be limited.
+- Toxicity: The model could inadvertently generate responses containing inappropriate or harmful content.
+
+## Acknowledgments
+We extend our heartfelt gratitude to the open-source AI community; this endeavor would not have been possible without open source. SambaNova embraces the open-source community and aspires to actively contribute to this initiative.
+
+We would like to give a special thanks to the following groups:
+- Meta for open sourcing LLama 2 and open sourcing FLORES-200 dataset
+- Nguyen et al for open sourcing CulturaX dataset
+- CohereAI for releasing AYA-101 and open sourcing a multilingual instruction tuning dataset
+- EleutherAI for their open source evaluation framework
+- Hugging Face-H4 team for open source the zephyr training recipe and alignment handbook repo
+
+
+## Cite SambaLingo
+```
+@misc{csaki2024sambalingo,
+      title={SambaLingo: Teaching Large Language Models New Languages}, 
+      author={Zoltan Csaki and Bo Li and Jonathan Li and Qiantong Xu and Pian Pawakapan and Leon Zhang and Yun Du and Hengyu Zhao and Changran Hu and Urmish Thakker},
+      year={2024},
+      eprint={2404.05829},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+

SambaLingo-Russian-Chat.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ca166971ef6e959da63452ee8c860dee6c0d489b81f48788ab5e1af1c4f060
+size 3992652960

SambaLingo-Russian-Chat.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dd346ed7ffebf530106ee1d73822a950a91871fd2d5d361598103528dc97de
+size 3788573856

SambaLingo-Russian-Chat.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f7de55ee738ba0d37303fb32bff705eaf774fa97657d37f971d3327cc18c27
+size 2652834976

SambaLingo-Russian-Chat.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8b53ab50a64f259fa1428006ffe1817d99ce1199b66c45bbbd004276965e52
+size 3428519072

SambaLingo-Russian-Chat.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ff55fcfbf1af631ad657472694172b3e5297b47ae106980f40378940326c51
+size 3727625376

SambaLingo-Russian-Chat.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8b53ab50a64f259fa1428006ffe1817d99ce1199b66c45bbbd004276965e52
+size 3428519072

SambaLingo-Russian-Chat.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b27ebb14e8714948357622dd9827777f07bf1f1c6603743ae00ef6fa1bbb396
+size 3078818976

SambaLingo-Russian-Chat.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865534ee3b08ca8fb0ed3f015c2fa9c1647ad0f1e8e4c7cbb10de1cc2ba283fa
+size 3970108576

SambaLingo-Russian-Chat.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5434f61b413bd04701e5dfc6700b189bc51165e1e6d3134e998b58ce0e2d1c7
+size 4389538976

SambaLingo-Russian-Chat.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a302c80063e4b37006c423b4ccb5b55df3cc188a27e4bd42b5068c53152f217e
+size 4225305760

SambaLingo-Russian-Chat.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a302c80063e4b37006c423b4ccb5b55df3cc188a27e4bd42b5068c53152f217e
+size 4225305760

SambaLingo-Russian-Chat.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350207fc55e8b2ded22642937e7e40f667fdfac5231adee7f2133299494573d6
+size 4001041568

SambaLingo-Russian-Chat.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad202b99b75d8847b51d51e68a2ff2b0fbf90fc3f3e878a855dce8cffe884b69
+size 4808969376

SambaLingo-Russian-Chat.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6581caefb8a3fe54e20dd3672cc59b8bcabfbfcf4e7c9fa39dea418ea24070d8
+size 5228399776

SambaLingo-Russian-Chat.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df58f1665830c22324c34aa98b2182b788db2b78682e41b661760fca441e41d0
+size 4940434592

SambaLingo-Russian-Chat.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df58f1665830c22324c34aa98b2182b788db2b78682e41b661760fca441e41d0
+size 4940434592

SambaLingo-Russian-Chat.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2228f0da792f9d24bde8a9aa1f787fb265cf1d78dce4e025f51a18f278825af3
+size 4808969376

SambaLingo-Russian-Chat.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506f78f1bea732adb00f3d99449848c3d37973da6561d2c1e94fb3f4104fb27e
+size 5700258976

SambaLingo-Russian-Chat.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7e9a4a74202e65fc4a7ff9dc9de4b8548a9aa3a0887cd7fd0f7660b31daf3c
+size 7382437024