burgasdotpro/wikipedia
Viewer • Updated • 9.59M • 1.33k
How to use burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B")
model = AutoModelForCausalLM.from_pretrained("burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B")
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]:]))How to use burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B
How to use burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B" \
--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": "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B" \
--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": "burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B",
max_seq_length=2048,
)How to use burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B with Docker Model Runner:
docker model run hf.co/burgasdotpro/bgGPT-DeepSeek-R1-Distill-Qwen-7B
МИСЛЕЩА модела базирана на най-новата DeepSeek-R1-Distill-Qwen-7B
Актуализиран 04.02.2025
Short text:
Perplexity (PPL) base model: 179.76
Perplexity (PPL) this model: 72.63
Long text:
Perplexity (PPL) base model: 258.56
Perplexity (PPL) this model: 83.96
Релиз 31.01.2025
Ти си българоезичен автоматичен асистент. Ползвател дава задача - трябва да предоставиш решение на Български език.
2x - 7 = 93. Определи x
<think>
Добре, ще помогна! Съм стигнал до тази задача: 2x - 7 = 93. Открием за x! Как ще я реша? Първо, ще използвам уравнението и ще се справя с променливите. Тъй като има 2x, това означава 2 по x, т.е. 2 умножено по неизвестниятour x. След това, ще извършва инвертиране на действията. Стъпка по стъпка, ще се извършва. Първо, ще съберем 7 от двете страни, за да намерим стойността на 2x. След това, ще разделим резултата на 2, за да намерим стойността на x. Пак, ще проверя, дали това е вярно, че 2x - 7 = 93, с x = 50. След това, ще използвам редовната ми методология за решаване на уравнения и ще се сподели стъпките, за да се получи x. Всички тези стъпки са логични и правилни, така че резултатът ще бъде точен. Мисля, че това е лесно и ясно, и ще се сподели с теб! <|im_end|>
</think>
Добре, ще помогна!
1. **Решаване на уравнението:**
- Начално, имаме уравнението: 2x - 7 = 93.
- Първо, извършваме инвертиране на действията. Стъпка по стъпка, ще се извършва.
- Първо, ще съберем 7 от двете страни, за да намерим стойността на 2x.
- 2x - 7 + 7 = 93 + 7
- 2x = 100
- След това, ще разделим резултата на 2, за да намерим стойността на x.
- 2x / 2 = 100 / 2
- x = 50
2. **Проверка на резултата:**
- Тъй като 2 * 50 - 7 = 100 - 7 = 93, това е вярно.
3. **Решение:**
- x = 50
Така че, резултатът е x = 50.
Тази qwen2 модела тренирана 2 пъти по-бързо с помоща на Unsloth и TRL библиотеката на Huggingface.
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B