Instructions to use stelterlab/Yi-Coder-9B-Chat-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stelterlab/Yi-Coder-9B-Chat-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="stelterlab/Yi-Coder-9B-Chat-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stelterlab/Yi-Coder-9B-Chat-AWQ")
model = AutoModelForCausalLM.from_pretrained("stelterlab/Yi-Coder-9B-Chat-AWQ")
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

vLLM

How to use stelterlab/Yi-Coder-9B-Chat-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stelterlab/Yi-Coder-9B-Chat-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stelterlab/Yi-Coder-9B-Chat-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stelterlab/Yi-Coder-9B-Chat-AWQ

SGLang

How to use stelterlab/Yi-Coder-9B-Chat-AWQ 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 "stelterlab/Yi-Coder-9B-Chat-AWQ" \
    --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": "stelterlab/Yi-Coder-9B-Chat-AWQ",
		"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 "stelterlab/Yi-Coder-9B-Chat-AWQ" \
        --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": "stelterlab/Yi-Coder-9B-Chat-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stelterlab/Yi-Coder-9B-Chat-AWQ with Docker Model Runner:
```
docker model run hf.co/stelterlab/Yi-Coder-9B-Chat-AWQ
```

Yi Coder 9B Chat by 01-Ai

Model creator: 01-ai
Original model: Yi-Coder-9B-Chat
AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper-hansen (https://github.com/casper-hansen/AutoAWQ/)

Model Summary:

Yi Coder 9B Chat is a new coding model from Yi, supporting a staggering 52 programming language, and featuring a max context length of 128k, making it great for ingesting large codebases.
This model is tuned for chatting, not auto completion, so should be chatted with for programming questions.
It is the first model under 10B parameters to pass 20% on LiveCodeBench.

Technical Details

Trained on an extensive set of languages:

java
markdown
python
php
javascript
c++
c#
c
typescript
html
go
java_server_pages
dart
objective-c
kotlin
tex
swift
ruby
sql
rust
css
yaml
matlab
lua
json
shell
visual_basic
scala
rmarkdown
pascal
fortran
haskell
assembly
perl
julia
cmake
groovy
ocaml
powershell
elixir
clojure
makefile
coffeescript
erlang
lisp
toml
batchfile
cobol
dockerfile
r
prolog
verilog

128k context length, achieves 23% pass rate on LiveCodeBench, surpassing even some SOTA 15-33B models.

For more information see original model card Yi-Coder-9B-Chat

Downloads last month: 10

Safetensors

Model size

9B params

Tensor type

I32

F16

Model tree for stelterlab/Yi-Coder-9B-Chat-AWQ

Base model

01-ai/Yi-Coder-9B

Finetuned

01-ai/Yi-Coder-9B-Chat

Quantized

(18)

this model