Instructions to use WisdomShell/CodeShell-7B-Chat-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WisdomShell/CodeShell-7B-Chat-int4 with Transformers:

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

pipe = pipeline("text-generation", model="WisdomShell/CodeShell-7B-Chat-int4", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("WisdomShell/CodeShell-7B-Chat-int4", trust_remote_code=True, dtype="auto")

llama-cpp-python

How to use WisdomShell/CodeShell-7B-Chat-int4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="WisdomShell/CodeShell-7B-Chat-int4",
	filename="codeshell-chat-q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use WisdomShell/CodeShell-7B-Chat-int4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0
# Run inference directly in the terminal:
llama-cli -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0
# Run inference directly in the terminal:
llama-cli -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WisdomShell/CodeShell-7B-Chat-int4:Q4_0

Use Docker

docker model run hf.co/WisdomShell/CodeShell-7B-Chat-int4:Q4_0

LM Studio
Jan

vLLM

How to use WisdomShell/CodeShell-7B-Chat-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WisdomShell/CodeShell-7B-Chat-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WisdomShell/CodeShell-7B-Chat-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WisdomShell/CodeShell-7B-Chat-int4:Q4_0

SGLang

How to use WisdomShell/CodeShell-7B-Chat-int4 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 "WisdomShell/CodeShell-7B-Chat-int4" \
    --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": "WisdomShell/CodeShell-7B-Chat-int4",
		"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 "WisdomShell/CodeShell-7B-Chat-int4" \
        --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": "WisdomShell/CodeShell-7B-Chat-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use WisdomShell/CodeShell-7B-Chat-int4 with Ollama:
```
ollama run hf.co/WisdomShell/CodeShell-7B-Chat-int4:Q4_0
```

Unsloth Studio new

How to use WisdomShell/CodeShell-7B-Chat-int4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

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 WisdomShell/CodeShell-7B-Chat-int4 to start chatting

Install Unsloth Studio (Windows)

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 WisdomShell/CodeShell-7B-Chat-int4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WisdomShell/CodeShell-7B-Chat-int4 to start chatting

Docker Model Runner
How to use WisdomShell/CodeShell-7B-Chat-int4 with Docker Model Runner:
```
docker model run hf.co/WisdomShell/CodeShell-7B-Chat-int4:Q4_0
```

Lemonade

How to use WisdomShell/CodeShell-7B-Chat-int4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WisdomShell/CodeShell-7B-Chat-int4:Q4_0

Run and chat with the model

lemonade run user.CodeShell-7B-Chat-int4-Q4_0

List all available models

lemonade list

CodeShell-7B-Chat-int4 在TGI下运行失败

by melonrindrind - opened Oct 23, 2023

Discussion

melonrindrind

Oct 23, 2023

你好，感谢开发者们开源项目，在本地使用TGI运行过程中我遇到了一些问题，由于3090显存不足无法运行7B未量化模型，我打算运行int4的量化模型，但 CodeShell-7B-Chat-int4 在TGI下运行失败,请问是什么问题

docker run --gpus 'all' --shm-size 20g -p 9090:80 -v /root/codeshell/model:/data         --env LOG_LEVEL="info,text_generation_router=debug"         ghcr.nju.edu.cn/huggingface/text-generation-inference:1.0.3         --model-id /data/C
odeShell-7B-Chat-int4 --num-shard 1         --max-total-tokens 5000 --max-input-length 4096         --max-stop-sequences 12 --trust-remote-code
2023-10-23T02:59:41.362133Z  INFO text_generation_launcher: Args { model_id: "/data/CodeShell-7B-Chat-int4", revision: None, validation_workers: 2, sharded: None, num_shard: Some(1), quantize: None, dtype: None, trust_remote_code: true, max_concurrent_requests: 128, max_best_of: 2, max_stop_sequences: 12, max_top_n_tokens: 5, max_input_length: 4096, max_total_tokens: 5000, waiting_served_ratio: 1.2, max_batch_prefill_tokens: 4096, max_batch_total_tokens: None, max_waiting_tokens: 20, hostname: "f1b26d576e27", port: 80, shard_uds_path: "/tmp/text-generation-server", master_addr: "localhost", master_port: 29500, huggingface_hub_cache: Some("/data"), weights_cache_override: None, disable_custom_kernels: false, cuda_memory_fraction: 1.0, rope_scaling: None, rope_factor: None, json_output: false, otlp_endpoint: None, cors_allow_origin: [], watermark_gamma: None, watermark_delta: None, ngrok: false, ngrok_authtoken: None, ngrok_edge: None, env: false }
2023-10-23T02:59:41.362173Z  WARN text_generation_launcher: `trust_remote_code` is set. Trusting that model `/data/CodeShell-7B-Chat-int4` do not contain malicious code.
2023-10-23T02:59:41.362290Z  INFO download: text_generation_launcher: Starting download process.
2023-10-23T02:59:44.612287Z  WARN text_generation_launcher: No safetensors weights found for model /data/CodeShell-7B-Chat-int4 at revision None. Converting PyTorch weights to safetensors.

Error: DownloadError
2023-10-23T02:59:47.269640Z ERROR download: text_generation_launcher: Download encountered an error: Traceback (most recent call last):

  File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())

  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/cli.py", line 195, in download_weights
    utils.convert_files(local_pt_files, local_st_files, discard_names)

  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/convert.py", line 106, in convert_files
    convert_file(pt_file, sf_file, discard_names)

  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/convert.py", line 68, in convert_file
    to_removes = _remove_duplicate_names(loaded, discard_names=discard_names)

  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/convert.py", line 25, in _remove_duplicate_names
    shareds = _find_shared_tensors(state_dict)

  File "/opt/conda/lib/python3.9/site-packages/safetensors/torch.py", line 72, in _find_shared_tensors
    if v.device != torch.device("meta") and storage_ptr(v) != 0 and storage_size(v) != 0:

AttributeError: 'list' object has no attribute 'device'

apkai

Oct 24, 2023

蹲，同样的问题

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment