Instructions to use stevenbowler/MedChatBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stevenbowler/MedChatBot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="stevenbowler/MedChatBot")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("stevenbowler/MedChatBot") model = AutoModelForCausalLM.from_pretrained("stevenbowler/MedChatBot") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use stevenbowler/MedChatBot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "stevenbowler/MedChatBot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "stevenbowler/MedChatBot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/stevenbowler/MedChatBot
- SGLang
How to use stevenbowler/MedChatBot 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 "stevenbowler/MedChatBot" \ --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": "stevenbowler/MedChatBot", "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 "stevenbowler/MedChatBot" \ --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": "stevenbowler/MedChatBot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use stevenbowler/MedChatBot with Docker Model Runner:
docker model run hf.co/stevenbowler/MedChatBot
Commit ·
4d5ab8b
1
Parent(s): 58666d4
Upload LlamaForCausalLM
Browse files- config.json +1 -1
- pytorch_model.bin +3 -0
config.json
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"rope_scaling": null,
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
-
"torch_dtype": "
|
| 22 |
"transformers_version": "4.32.0",
|
| 23 |
"use_cache": true,
|
| 24 |
"vocab_size": 32000
|
|
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"rope_scaling": null,
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.32.0",
|
| 23 |
"use_cache": true,
|
| 24 |
"vocab_size": 32000
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80a206458e0c9aa2ac884752cf82941b283b87c8aae2c24710ae9d0140d6576e
|
| 3 |
+
size 7810136375
|