Instructions to use med-rcq/MedQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use med-rcq/MedQA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="med-rcq/MedQA", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("med-rcq/MedQA", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("med-rcq/MedQA", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use med-rcq/MedQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "med-rcq/MedQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "med-rcq/MedQA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/med-rcq/MedQA

SGLang

How to use med-rcq/MedQA 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 "med-rcq/MedQA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "med-rcq/MedQA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "med-rcq/MedQA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "med-rcq/MedQA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use med-rcq/MedQA with Docker Model Runner:
```
docker model run hf.co/med-rcq/MedQA
```

dsayed commited on Aug 20, 2024

Commit

aaa1f74

verified ·

1 Parent(s): 8d1ba05

Upload folder using huggingface_hub

Browse files

Files changed (11) hide show

config.json +1 -1
generation_config.json +1 -1
model-00001-of-00008.safetensors +1 -1
model-00002-of-00008.safetensors +1 -1
model-00003-of-00008.safetensors +1 -1
model-00004-of-00008.safetensors +1 -1
model-00005-of-00008.safetensors +1 -1
model-00006-of-00008.safetensors +1 -1
model-00007-of-00008.safetensors +1 -1
model-00008-of-00008.safetensors +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -31,7 +31,7 @@
   "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 32064
 }

   "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
     32007
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.43.3"
 }

     32007
   ],
   "pad_token_id": 32000,
+  "transformers_version": "4.43.4"
 }

model-00001-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f676f2369169f3115a6b01e3929802fbce8698041d0c552c149f406acd4bc3
 size 3867385624

 version https://git-lfs.github.com/spec/v1
+oid sha256:0e2f968158394471269331ed7217fc9d9b6225bad5fbc39e30e3cfb6e2d79844
 size 3867385624

model-00002-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0859ea3fc36220167e351b0aedbcd1b6377a64e6847281f3047666f0d5c385ea
 size 3958501264

 version https://git-lfs.github.com/spec/v1
+oid sha256:72e848009b9f581948932e67a0c7a1d78053e388cc1e35fb6c2eb18047e62c7c
 size 3958501264

model-00003-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4580a76e5e27f53f229c7a987445c353dc6bead82ec345ddb84914a33701b63a
 size 3906051896

 version https://git-lfs.github.com/spec/v1
+oid sha256:f3f43dbf164e82f4db1bb46c883f45edf26f7e5b50994e5b8bb4b2a4d08301ff
 size 3906051896

model-00004-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e8ff2f694a210d6beab1cc21e7839329438ccf42437b0bd5350e67fd87184e
 size 3722571800

 version https://git-lfs.github.com/spec/v1
+oid sha256:e79a430575ce0489b8b3696acb8596f6aef56af38e7565ec472cf2130982b21d
 size 3722571800

model-00005-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8119e53495e65b1723f44ab5a6e9497f6785af170d5959d21fe75d65cc59eeed
 size 3958501296

 version https://git-lfs.github.com/spec/v1
+oid sha256:adeec84379bc31c592b3aaca12933906d85f23239347fe22f33fbaed3d229e0a
 size 3958501296

model-00006-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6815119cd0aa262ed78a9db9d7bf16b5501c3a881152192a874a7bdf349819
 size 3906051896

 version https://git-lfs.github.com/spec/v1
+oid sha256:636abd25e9e8087111ff4c3117c6ac59853234fa69c5c955983f21650258932c
 size 3906051896

model-00007-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f552c686a0b4f699b9347c7facae9842f4eed93bd6bff78047a2552fafd3a8
 size 3722571800

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb16e65f9d747d9a13bc9febeeb8584ce3e3b5f35050bf7532ec7800f18e62d5
 size 3722571800

model-00008-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e9ec0f35ab5f0cc3ae2c7e821067089d1d6c4d6c6ec00cc9672653009f03fd
 size 878869160

 version https://git-lfs.github.com/spec/v1
+oid sha256:800f27cf9c0b7e82216e8b9c7ac06936bee50f978f3a8b8b573181c2add36180
 size 878869160

tokenizer_config.json CHANGED Viewed

@@ -117,7 +117,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|end|>",
   "legacy": false,

     }
   },
   "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|end|>",
   "legacy": false,