Instructions to use liminerity/Bitnet-Mistral.0.2-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/Bitnet-Mistral.0.2-v3 with Transformers:

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

pipe = pipeline("text-generation", model="liminerity/Bitnet-Mistral.0.2-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liminerity/Bitnet-Mistral.0.2-v3")
model = AutoModelForCausalLM.from_pretrained("liminerity/Bitnet-Mistral.0.2-v3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liminerity/Bitnet-Mistral.0.2-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liminerity/Bitnet-Mistral.0.2-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/Bitnet-Mistral.0.2-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liminerity/Bitnet-Mistral.0.2-v3

SGLang

How to use liminerity/Bitnet-Mistral.0.2-v3 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 "liminerity/Bitnet-Mistral.0.2-v3" \
    --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": "liminerity/Bitnet-Mistral.0.2-v3",
		"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 "liminerity/Bitnet-Mistral.0.2-v3" \
        --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": "liminerity/Bitnet-Mistral.0.2-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liminerity/Bitnet-Mistral.0.2-v3 with Docker Model Runner:
```
docker model run hf.co/liminerity/Bitnet-Mistral.0.2-v3
```

gate369 commited on Jun 23, 2024

Commit

01399a2

verified ·

1 Parent(s): 6e2a852

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

config.json +1 -1
model.safetensors +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./Bitnet-Mistral.0.2-v2-2048/final_model/",
   "architectures": [
     "MistralForCausalLM"
   ],

 {
+  "_name_or_path": "./Bitnet-Mistral.0.2-v2-2048-2/final_model/",
   "architectures": [
     "MistralForCausalLM"
   ],

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29fed27fcd30e4be8330948e1bdeab812646f4c0d6009c68561529dc4368f2b5
 size 128524840

 version https://git-lfs.github.com/spec/v1
+oid sha256:9363578391e3fe36635e2186246ce4115226e896f584cc44c6d859f1a9bb0514
 size 128524840

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9c2939095aa18b1f4c9094def5df2952f15bdc419923738c747cfc214bf696
 size 5112

 version https://git-lfs.github.com/spec/v1
+oid sha256:a181d705e5d49f61c5b096b4c5ea18af9c48a029138084e304570864fb754d4c
 size 5112