Instructions to use swj0419/7b_standard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use swj0419/7b_standard with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="swj0419/7b_standard")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("swj0419/7b_standard") model = AutoModelForCausalLM.from_pretrained("swj0419/7b_standard") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use swj0419/7b_standard with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "swj0419/7b_standard" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "swj0419/7b_standard", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/swj0419/7b_standard
- SGLang
How to use swj0419/7b_standard 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 "swj0419/7b_standard" \ --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": "swj0419/7b_standard", "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 "swj0419/7b_standard" \ --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": "swj0419/7b_standard", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use swj0419/7b_standard with Docker Model Runner:
docker model run hf.co/swj0419/7b_standard
Upload LlamaForCausalLM
Browse files- config.json +1 -1
- pytorch_model-00001-of-00003.bin +1 -1
- pytorch_model-00002-of-00003.bin +1 -1
- pytorch_model-00003-of-00003.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/fsx-onellm/swj0419/rlm_pretrain/xldumps/5-4/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/fsx-onellm/swj0419/rlm_pretrain/xldumps/5-4/sort_7b/sort_7b_run000/checkpoints/checkpoint_0125000_consolidated_hf",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
pytorch_model-00001-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9877989586
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f232f49dcc20c5173b592a88b3b2b7320ff4d7b19ab2340698dfec6e02c66edb
|
| 3 |
size 9877989586
|
pytorch_model-00002-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9894801014
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24eb1ca1efbc0e43092f8898bd8f454a86002313e6a10d20af1836723d7fc8bd
|
| 3 |
size 9894801014
|
pytorch_model-00003-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7180990649
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:707727aa724c798fd6bcd276fc5e70fbdc3dfc74d4b52203bc838a95587d1254
|
| 3 |
size 7180990649
|