Instructions to use opentensor/bt-opt-1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opentensor/bt-opt-1.3b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="opentensor/bt-opt-1.3b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("opentensor/bt-opt-1.3b") model = AutoModelForCausalLM.from_pretrained("opentensor/bt-opt-1.3b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use opentensor/bt-opt-1.3b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "opentensor/bt-opt-1.3b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "opentensor/bt-opt-1.3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/opentensor/bt-opt-1.3b
- SGLang
How to use opentensor/bt-opt-1.3b 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 "opentensor/bt-opt-1.3b" \ --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": "opentensor/bt-opt-1.3b", "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 "opentensor/bt-opt-1.3b" \ --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": "opentensor/bt-opt-1.3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use opentensor/bt-opt-1.3b with Docker Model Runner:
docker model run hf.co/opentensor/bt-opt-1.3b
carro commited on
Commit ·
d0d4580
1
Parent(s): 4a6599f
v1.0.0
Browse files- README.md +0 -3
- config.json +2 -2
- pytorch_model.bin +2 -2
README.md
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -21,8 +21,8 @@
|
|
| 21 |
"num_hidden_layers": 24,
|
| 22 |
"pad_token_id": 1,
|
| 23 |
"prefix": "</s>",
|
| 24 |
-
"torch_dtype": "
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 50265,
|
| 28 |
"word_embed_proj_dim": 2048
|
|
|
|
| 21 |
"num_hidden_layers": 24,
|
| 22 |
"pad_token_id": 1,
|
| 23 |
"prefix": "</s>",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.22.1",
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 50265,
|
| 28 |
"word_embed_proj_dim": 2048
|
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:af6c08bf81da38b6035166ec9825880a36ce1d727bfd02e9a9bd6b3d135dcbbb
|
| 3 |
+
size 714008448
|