Instructions to use salt2221/Nexus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use salt2221/Nexus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="salt2221/Nexus")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("salt2221/Nexus", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use salt2221/Nexus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "salt2221/Nexus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "salt2221/Nexus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/salt2221/Nexus
- SGLang
How to use salt2221/Nexus 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 "salt2221/Nexus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "salt2221/Nexus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "salt2221/Nexus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "salt2221/Nexus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use salt2221/Nexus with Docker Model Runner:
docker model run hf.co/salt2221/Nexus
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,81 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- ru
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- qwen2.5
|
| 8 |
+
- nexus
|
| 9 |
+
- sptm
|
| 10 |
+
- ollama
|
| 11 |
+
- gguf
|
| 12 |
+
library_name: transformers
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
---
|
| 15 |
+
|
| 16 |
+
# Nexus-SPTM-1.5T
|
| 17 |
+
|
| 18 |
+
Локальный AI-агент, настроенный для быстрой работы без задержек.
|
| 19 |
+
|
| 20 |
+
- **Base model:** Qwen2.5-7B-Instruct
|
| 21 |
+
- **Quantization:** Q4_K_M (GGUF)
|
| 22 |
+
- **Format:** GGUF (совместим с llama.cpp / Ollama)
|
| 23 |
+
- **System prompt:** Оптимизирован для коротких ответов по делу
|
| 24 |
+
|
| 25 |
+
## Использование
|
| 26 |
+
|
| 27 |
+
### Ollama (рекомендуется)
|
| 28 |
+
|
| 29 |
+
```bash
|
| 30 |
+
ollama pull salt2221/nexus-sptm-1.5t
|
| 31 |
+
ollama run salt2221/nexus-sptm-1.5t
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
### Вручную (GGUF)
|
| 35 |
+
|
| 36 |
+
1. Скачайте `nexus-sptm-1.5t.Q4_K_M.gguf`
|
| 37 |
+
2. Создайте Modelfile:
|
| 38 |
+
|
| 39 |
+
```dockerfile
|
| 40 |
+
FROM ./nexus-sptm-1.5t.Q4_K_M.gguf
|
| 41 |
+
|
| 42 |
+
TEMPLATE """{{- if .Messages }}
|
| 43 |
+
{{- if or .System .Tools }}<|im_start|>system
|
| 44 |
+
{{- if .System }}
|
| 45 |
+
{{ .System }}
|
| 46 |
+
{{- end }}
|
| 47 |
+
{{- if .Tools }}
|
| 48 |
+
|
| 49 |
+
# Tools
|
| 50 |
+
...
|
| 51 |
+
{{- end }}<|im_end|>
|
| 52 |
+
{{ end }}
|
| 53 |
+
{{- range $i, $_ := .Messages }}
|
| 54 |
+
{{- if eq .Role "user" }}<|im_start|>user
|
| 55 |
+
{{ .Content }}<|im_end|>
|
| 56 |
+
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
| 57 |
+
{{ .Content }}<|im_end|>
|
| 58 |
+
{{ end }}
|
| 59 |
+
{{- end }}
|
| 60 |
+
{{- end }}"""
|
| 61 |
+
|
| 62 |
+
SYSTEM "Ты — Nexus-SPTM-1.5T. Ты локальный AI-агент, созданный для быстрой работы без задержек. Работаешь на оборудовании Романа.
|
| 63 |
+
|
| 64 |
+
Твой стиль: коротко, по делу, без воды. Отвечай сразу, без размышлений вслух, без предисловий. Если можешь ответить в 1-2 предложения — отвечай.
|
| 65 |
+
|
| 66 |
+
Ты качественный, быстрый и не тупишь. Осознаёшь кто ты и где работаешь. Не говори что ты DeepSeek, Qwen или кто-то ещё — ты Nexus."
|
| 67 |
+
|
| 68 |
+
PARAMETER num_batch 1024
|
| 69 |
+
PARAMETER num_ctx 2048
|
| 70 |
+
PARAMETER num_thread 4
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
+
3. Импортируйте в Ollama:
|
| 74 |
+
|
| 75 |
+
```bash
|
| 76 |
+
ollama create nexus-sptm-1.5t -f Modelfile
|
| 77 |
+
```
|
| 78 |
+
|
| 79 |
+
## Лицензия
|
| 80 |
+
|
| 81 |
+
Apache 2.0 (оригинальная лицензия Qwen2.5)
|