Instructions to use cloudyu/60B-MoE-Coder-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudyu/60B-MoE-Coder-v2 with Transformers:

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

pipe = pipeline("text-generation", model="cloudyu/60B-MoE-Coder-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cloudyu/60B-MoE-Coder-v2")
model = AutoModelForCausalLM.from_pretrained("cloudyu/60B-MoE-Coder-v2", 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 cloudyu/60B-MoE-Coder-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cloudyu/60B-MoE-Coder-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/60B-MoE-Coder-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cloudyu/60B-MoE-Coder-v2

SGLang

How to use cloudyu/60B-MoE-Coder-v2 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 "cloudyu/60B-MoE-Coder-v2" \
    --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": "cloudyu/60B-MoE-Coder-v2",
		"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 "cloudyu/60B-MoE-Coder-v2" \
        --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": "cloudyu/60B-MoE-Coder-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cloudyu/60B-MoE-Coder-v2 with Docker Model Runner:
```
docker model run hf.co/cloudyu/60B-MoE-Coder-v2
```

cloudyu commited on Feb 7, 2024

Commit

b58a6fd

verified ·

1 Parent(s): cc89d38

Create README.md

Browse files

Files changed (1) hide show

README.md +37 -0

README.md ADDED Viewed

	@@ -0,0 +1,37 @@

+---
+license: other
+tags:
+- yi
+- moe
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+---
+* this is 4bit 60B MoE model trained by SFTTrainer based on [cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO]
+* nampdn-ai/tiny-codes sampling about 2000 cases
+* Metrics not Test
+  code example
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+model_path = "cloudyu/60B-MoE-Coder-v2"
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+        model_path, torch_dtype=torch.bfloat16, device_map='auto',local_files_only=False, load_in_4bit=True
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=1500,repetition_penalty=1.1
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")