Instructions to use Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2")
model = AutoModelForCausalLM.from_pretrained("Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2", 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 Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2

SGLang

How to use Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2 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 "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2" \
    --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": "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2",
		"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 "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2" \
        --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": "Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2 with Docker Model Runner:
```
docker model run hf.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2
```

Zoyd commited on May 21, 2024

Commit

14fcc1d

verified ·

1 Parent(s): 7a30fd2

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -1,6 +1,23 @@
 ---
 license: apache-2.0
 ---
 <div align="center">
 <picture>

 ---
 license: apache-2.0
 ---
+**Exllamav2** quant (**exl2** / **2.2 bpw**) made with ExLlamaV2 v0.0.21
+Other EXL2 quants:
+| **Quant** | **Model Size** | **lm_head** |
+| ----- | ---------- | ------- |
+|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_2bpw_exl2)**</center> | <center>10049 MB</center> | <center>6</center> |
+|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-2_5bpw_exl2)**</center> | <center>11195 MB</center> | <center>6</center> |
+|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-3_0bpw_exl2)**</center> | <center>13193 MB</center> | <center>6</center> |
+|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-3_5bpw_exl2)**</center> | <center>15187 MB</center> | <center>6</center> |
+|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-3_75bpw_exl2)**</center> | <center>16186 MB</center> | <center>6</center> |
+|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-4_0bpw_exl2)**</center> | <center>17183 MB</center> | <center>6</center> |
+|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-4_25bpw_exl2)**</center> | <center>18179 MB</center> | <center>6</center> |
+|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-5_0bpw_exl2)**</center> | <center>21171 MB</center> | <center>6</center> |
+|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-6_0bpw_exl2)**</center> | <center>25231 MB</center> | <center>8</center> |
+|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-6_5bpw_exl2)**</center> | <center>27111 MB</center> | <center>8</center> |
+|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-34B-Chat-16K-8_0bpw_exl2)**</center> | <center>29540 MB</center> | <center>8</center> |
 <div align="center">
 <picture>