Instructions to use player1537/Dolphinette with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use player1537/Dolphinette with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="player1537/Dolphinette")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("player1537/Dolphinette") model = AutoModelForCausalLM.from_pretrained("player1537/Dolphinette", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use player1537/Dolphinette with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "player1537/Dolphinette" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "player1537/Dolphinette", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/player1537/Dolphinette
- SGLang
How to use player1537/Dolphinette 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 "player1537/Dolphinette" \ --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": "player1537/Dolphinette", "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 "player1537/Dolphinette" \ --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": "player1537/Dolphinette", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use player1537/Dolphinette with Docker Model Runner:
docker model run hf.co/player1537/Dolphinette
Commit ·
2ac2b8b
1
Parent(s): 755807e
Upload BloomForCausalLM
Browse files- config.json +1 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"skip_bias_add": true,
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
-
"torch_dtype": "
|
| 28 |
"transformers_version": "4.32.1",
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
|
|
|
| 24 |
"skip_bias_add": true,
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
"transformers_version": "4.32.1",
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
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 sha256:6c6acd3e802983ab74e236df8d260a4c702413a8738e5c34789e4dc439298347
|
| 3 |
+
size 1118524193
|