Instructions to use lmsys/vicuna-33b-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmsys/vicuna-33b-v1.3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lmsys/vicuna-33b-v1.3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lmsys/vicuna-33b-v1.3") model = AutoModelForCausalLM.from_pretrained("lmsys/vicuna-33b-v1.3") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lmsys/vicuna-33b-v1.3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmsys/vicuna-33b-v1.3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmsys/vicuna-33b-v1.3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lmsys/vicuna-33b-v1.3
- SGLang
How to use lmsys/vicuna-33b-v1.3 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 "lmsys/vicuna-33b-v1.3" \ --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": "lmsys/vicuna-33b-v1.3", "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 "lmsys/vicuna-33b-v1.3" \ --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": "lmsys/vicuna-33b-v1.3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lmsys/vicuna-33b-v1.3 with Docker Model Runner:
docker model run hf.co/lmsys/vicuna-33b-v1.3
Upload LlamaForCausalLM
Browse files
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "vicuna-
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/ubuntu/model_weights/vicuna-33b-gpt4-20230521/",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
pytorch_model-00001-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9818324627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde176666dbac70c86826fc33aafc83757589ce4d601699c1cbe19b3992f467d
|
| 3 |
size 9818324627
|
pytorch_model-00002-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9958102743
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d8a9482098194e48b67bd26c5af0bf4af4ce2e4aea3e4afbe4d41585f3eba7
|
| 3 |
size 9958102743
|
pytorch_model-00003-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9896734715
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14f40574376c5475e0b6af703fb4d9b0a8addcd63a2805c3069bb2ef8dcda583
|
| 3 |
size 9896734715
|
pytorch_model-00004-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9869470481
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:445c09eaaef05a199f775733a0a66a50da5dae1f68b8f484178cbd8aed5f5b67
|
| 3 |
size 9869470481
|
pytorch_model-00005-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9869470445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9efc61a84386c71a53128be066c6c8eaf5ecd0346b787656a81fcec6d1491d
|
| 3 |
size 9869470445
|
pytorch_model-00006-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9958102743
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1751cd8ea5c34a4ecf92602c90952b768a25c71a193abfc7e91d6d694a0900b
|
| 3 |
size 9958102743
|
pytorch_model-00007-of-00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5687903281
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83b05caa9d26bcf406a1108b7e314e14edfab2cf9d3d4a21e2dac782d53a60ae
|
| 3 |
size 5687903281
|