Instructions to use InMedData/InMD-X-ALL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InMedData/InMD-X-ALL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="InMedData/InMD-X-ALL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("InMedData/InMD-X-ALL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use InMedData/InMD-X-ALL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "InMedData/InMD-X-ALL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "InMedData/InMD-X-ALL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/InMedData/InMD-X-ALL
- SGLang
How to use InMedData/InMD-X-ALL 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 "InMedData/InMD-X-ALL" \ --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": "InMedData/InMD-X-ALL", "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 "InMedData/InMD-X-ALL" \ --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": "InMedData/InMD-X-ALL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use InMedData/InMD-X-ALL with Docker Model Runner:
docker model run hf.co/InMedData/InMD-X-ALL
Upload model
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "/
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -20,10 +20,10 @@
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"gate_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
-
"q_proj",
|
| 25 |
"v_proj",
|
|
|
|
| 26 |
"down_proj",
|
|
|
|
| 27 |
"up_proj",
|
| 28 |
"o_proj"
|
| 29 |
],
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Intel/neural-chat-7b-v3-1",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"gate_proj",
|
|
|
|
|
|
|
| 23 |
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
"up_proj",
|
| 28 |
"o_proj"
|
| 29 |
],
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ffdf4af896456ca85927dd4d79aa7ce0f648269f758e2faaa9aeae9eec10c3
|
| 3 |
size 83945296
|