Instructions to use attn-signs/Watari-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use attn-signs/Watari-7b-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="attn-signs/Watari-7b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("attn-signs/Watari-7b-v1")
model = AutoModelForCausalLM.from_pretrained("attn-signs/Watari-7b-v1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use attn-signs/Watari-7b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "attn-signs/Watari-7b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "attn-signs/Watari-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/attn-signs/Watari-7b-v1

SGLang

How to use attn-signs/Watari-7b-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "attn-signs/Watari-7b-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "attn-signs/Watari-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "attn-signs/Watari-7b-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "attn-signs/Watari-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use attn-signs/Watari-7b-v1 with Docker Model Runner:
```
docker model run hf.co/attn-signs/Watari-7b-v1
```

attn-signs commited on Feb 20, 2025

Commit

0b52b2f

verified ·

1 Parent(s): 619e9dd

Update README.md

Browse files

Files changed (1) hide show

README.md +72 -166

README.md CHANGED Viewed

@@ -3,197 +3,103 @@ 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]

 tags: []
 ---
+# Watari 7B (V2)
+- [EN]
+Qwen2.5-based model, adapted for russian text generation tasks.
+This is a base SFT version for further reasoning development and alignment.
+- [RU]
+Finetune версия Qwen2.5, адаптированная для генерации русского текста.
+Является SFT базой для дальнейших ризонинг-оптимизаций с GRPO и алайнмента.
+### Huge thanks to mradermacher for converting all models to GGUF format!
+The further conversions/upgrade are much appreciated and welcomed, feel free to join.
+[https://huggingface.co/mradermacher/Watari-7b-v0-GGUF]
+[https://huggingface.co/mradermacher/Watari-7b-v0.5-GGUF]
+**Repo id:** mradermacher/Watari-7b-v0-GGUF
+**Repo id:** mradermacher/Watari-7b-v0.5-GGUF
+### Previous model states (considering epoch %):
+- Watari-7b-v0
+- Watari-7b-v0.5
+## Model Details / Детализация модели
+- [EN]
+Full supervised finetuning was performed on 2xA100 NVIDIA GPUs for ~7 days for 1 epoch on dataset:
+GrandMaster [Vikhrmodels/GrandMaster-PRO-MAX]
+- [RU]
+Полный SFT цикл (bfloat16, без низкоранговых адаптеров LoRa) был выполнен на двух NVIDIA A100, обучение длилось около 7 дней.
+Прогон полной эпохи датасета GrandMaster [Vikhrmodels/GrandMaster-PRO-MAX]
+### Model Description / Описание модели
+- **Developed by:** [Reisen Raumberg (Attention Signs team)]
+- **Language(s) (NLP):** [RU/EN]
+- **Finetuned from model:** [Qwen2.5]
+Utilized DeepSpeed (Stage 3), HF.Accelerator for distributed training and fused AdamW.
+**GPU hours**: 336h of NVIDIA A100
+Для обучения использовались HuggingFace Accelerator с Microsoft DeepSpeed (Stage 3) для распределения параметров и стейта оптимизатора, а так же зафьюженный AdamW
+**GPU часы**: 336 часов NVIDIA A100
+### Using the model / Как запустить?
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+repo = 'attn-signs/Watari-7b-v1'
+model = AutoModelForCausalLM.from_pretrained(repo)
+tokenizer = AutoTokenizer.from_pretrained(repo)
+model.to('cuda')
+prompt = 'Что такое чёрная дыра? Напиши мне её уравнение'
+messages = [
+    {"role": "system", "content": "Ты Ватари, ассистент и помощник в решении различных задач. Отвечай на вопросы пользователя, рассуждая."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+```
+Тензор Риччи — это тензорная величина в дифференциальной геометрии, которая описывает кривизну многообразия. Он играет важную роль в общей теории относительности и других областях математики.
+В общем виде тензор Риччи \( R_{ij} \) опред��ляется через тензор Римана \( R^k_{ijkj} \) следующим образом:
+\[ R_{ij} = R^k_{ijkj} \]
+Это уравнение показывает, что тензор Риччи является суммированием по индексу \( k \) компонент тензора Римана, которые соответствуют компонентам метрического тензора \( g_{ij} \). Таким образом, тензор Риччи учитывает информацию о кривизне во всех направлениях в каждой точке многообразия.
+Тензор Риччи также связан с скалярной кривизной \( R \), которая получается путем дальнейшего суммирования:
+\[ R = g^{ij}R_{ij} \]
+Скалярная кривизна является мерой того, насколько многообразие отличается от плоского (плоское многообразие имеет скалярную кривизну равную нулю).
+В контексте общей теории относительности, тензор Риччи связывает массу и энергию (описываемые тензором энергии-импульса) с геометрией пространства-времени (описываемой метрикой). Это выражается уравнением Эйнштейна:
+\[ G_{ij} = 8\pi T_{ij} \]
+где \( G_{ij} \) — тензор Эйнштейна, который является тензором Риччи, уменьшенным на константу, а \( T_{ij} \) — тензор энергии-импульса.
+Таким образом, тензор Риччи является ключевым понятием в изучении геометрии многообразий и их взаимодействия с материей и энергией.
+```