Instructions to use DanceLab/cheese-llm-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DanceLab/cheese-llm-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DanceLab/cheese-llm-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DanceLab/cheese-llm-v1") model = AutoModelForCausalLM.from_pretrained("DanceLab/cheese-llm-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DanceLab/cheese-llm-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DanceLab/cheese-llm-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DanceLab/cheese-llm-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DanceLab/cheese-llm-v1
- SGLang
How to use DanceLab/cheese-llm-v1 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 "DanceLab/cheese-llm-v1" \ --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": "DanceLab/cheese-llm-v1", "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 "DanceLab/cheese-llm-v1" \ --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": "DanceLab/cheese-llm-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DanceLab/cheese-llm-v1 with Docker Model Runner:
docker model run hf.co/DanceLab/cheese-llm-v1
update int8 model
Browse files- config.json +2 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/data3/lk/llm/model/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -26,5 +26,5 @@
|
|
| 26 |
"torch_dtype": "float16",
|
| 27 |
"transformers_version": "4.29.2",
|
| 28 |
"use_cache": true,
|
| 29 |
-
"vocab_size":
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/data3/lk/llm/model/pretrain_rezhihu_large_v6_2_54999_ckpt_convert_secure",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 26 |
"torch_dtype": "float16",
|
| 27 |
"transformers_version": "4.29.2",
|
| 28 |
"use_cache": true,
|
| 29 |
+
"vocab_size": 49953
|
| 30 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:908518766ec13cf6bf91b63da67b0bd2065e6cd6c14f84c9ab85b2bda7b62507
|
| 3 |
+
size 7300592839
|