MTSAIR
/

Cotype-Nano-4bit

@@ -1,199 +1,71 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## 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. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+license: llama3.2
+language:
+- ru
+- en
+pipeline_tag: text-generation
 ---
+# Cotype-Nano-4bit🤖
+Llama-3-Cotype-Nano-4bit – это LLM, которая весит меньше и работает быстрее чем Cotype-Nano, при этом сохраняя свои языковые способности
+Llama-3-Cotype-Nano-4bit is an LLM that is lighter and runs faster than Cotype-Nano, while maintaining its language capabilities.
+### Inference with vLLM
+```
+python3 -m vllm.entrypoints.openai.api_server --model MTSAIR/Cotype-Nano-4bit --port 8000
+```
+### Recommended generation parameters and system prompt
+```python
+import openai
+import pandas as pd
+from tqdm import tqdm
+openai.api_key = 'xxx'
+endpoint = 'http://localhost:8000/v1'
+model = 'MTSAIR/Cotype-Nano-4bit'
+openai.api_base = endpoint
+response = openai.ChatCompletion.create(
+    model=model,
+    temperature=0.0, # также допускается 0.2
+    frequency_penalty=0.0,
+    max_tokens=2048,
+    top_p=0.1, # также допускается 0.9
+    messages=[
+          {"role": "system", "content": "Ты — ИИ-помощник. Тебе дано задание: необходимо сгенерировать подробный и развернутый ответ."},
+          {"role": "user", "content": "Расскажи мне про ИИ, коротко"}
+        ]
+    )
+answer = response["choices"][0]["message"]["content"]
+print(answer)
+```
+### Inference with Huggingface
+```python
+from transformers import pipeline
+pipe = pipeline("text-generation", model="MTSAIR/Cotype-Nano-4bit", device="cuda")
+messages = [
+  {"role": "system", "content": "Ты — ИИ-помощник. Тебе дано задание: необходимо сгенерировать подробный и развернутый ответ."},
+  {"role": "user", "content": "Расскажи мне про ИИ"},
+]
+res = pipe(messages, max_length=1024)
+print(res[0]['generated_text'][1])
+```
+## Example request
+**Request:** Расскажи мне про ИИ, коротко
+#### Cotype-Nano-4bit response:
+> Искусственный интеллект (ИИ) — это область компьютерных наук, занимающаяся созданием машин, способных выполнять задачи, требующие человеческого интеллекта. ИИ может включать в себя различные технологии, такие как машинное обучение, глубокое обучение, обработка естественного языка и др. Основная цель ИИ — создание систем, которые могут адаптироваться к новым задачам и обучаться на основе опыта. Примеры применения ИИ включают распознавание речи, перевод текста, рекомендации в интернет-магазинах, управление автомобилями и многое другое.