Instructions to use echo840/Monkey with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use echo840/Monkey with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="echo840/Monkey", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("echo840/Monkey", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use echo840/Monkey with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "echo840/Monkey" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "echo840/Monkey", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/echo840/Monkey
- SGLang
How to use echo840/Monkey 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 "echo840/Monkey" \ --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": "echo840/Monkey", "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 "echo840/Monkey" \ --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": "echo840/Monkey", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use echo840/Monkey with Docker Model Runner:
docker model run hf.co/echo840/Monkey
change
Browse files- modeling_monkey.py +1 -1
- modeling_qwen.py +3 -3
modeling_monkey.py
CHANGED
|
@@ -26,7 +26,7 @@ try:
|
|
| 26 |
except ImportError:
|
| 27 |
rearrange = None
|
| 28 |
from torch import nn
|
| 29 |
-
from modeling_qwen import QWenModel,QWenPreTrainedModel,QWenLMHeadModel
|
| 30 |
SUPPORT_CUDA = torch.cuda.is_available()
|
| 31 |
SUPPORT_BF16 = SUPPORT_CUDA and torch.cuda.is_bf16_supported()
|
| 32 |
SUPPORT_FP16 = SUPPORT_CUDA and torch.cuda.get_device_capability(0)[0] >= 7
|
|
|
|
| 26 |
except ImportError:
|
| 27 |
rearrange = None
|
| 28 |
from torch import nn
|
| 29 |
+
from .modeling_qwen import QWenModel,QWenPreTrainedModel,QWenLMHeadModel
|
| 30 |
SUPPORT_CUDA = torch.cuda.is_available()
|
| 31 |
SUPPORT_BF16 = SUPPORT_CUDA and torch.cuda.is_bf16_supported()
|
| 32 |
SUPPORT_FP16 = SUPPORT_CUDA and torch.cuda.get_device_capability(0)[0] >= 7
|
modeling_qwen.py
CHANGED
|
@@ -36,15 +36,15 @@ SUPPORT_CUDA = torch.cuda.is_available()
|
|
| 36 |
SUPPORT_BF16 = SUPPORT_CUDA and torch.cuda.is_bf16_supported()
|
| 37 |
SUPPORT_FP16 = SUPPORT_CUDA and torch.cuda.get_device_capability(0)[0] >= 7
|
| 38 |
|
| 39 |
-
from configuration_qwen import QWenConfig
|
| 40 |
-
from qwen_generation_utils import (
|
| 41 |
HistoryType,
|
| 42 |
make_context,
|
| 43 |
decode_tokens,
|
| 44 |
get_stop_words_ids,
|
| 45 |
StopWordsLogitsProcessor,
|
| 46 |
)
|
| 47 |
-
from visual import VisionTransformer
|
| 48 |
|
| 49 |
|
| 50 |
logger = logging.get_logger(__name__)
|
|
|
|
| 36 |
SUPPORT_BF16 = SUPPORT_CUDA and torch.cuda.is_bf16_supported()
|
| 37 |
SUPPORT_FP16 = SUPPORT_CUDA and torch.cuda.get_device_capability(0)[0] >= 7
|
| 38 |
|
| 39 |
+
from .configuration_qwen import QWenConfig
|
| 40 |
+
from .qwen_generation_utils import (
|
| 41 |
HistoryType,
|
| 42 |
make_context,
|
| 43 |
decode_tokens,
|
| 44 |
get_stop_words_ids,
|
| 45 |
StopWordsLogitsProcessor,
|
| 46 |
)
|
| 47 |
+
from .visual import VisionTransformer
|
| 48 |
|
| 49 |
|
| 50 |
logger = logging.get_logger(__name__)
|