Instructions to use Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3 with Transformers:

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

pipe = pipeline("text-generation", model="Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3")
model = AutoModelForMultimodalLM.from_pretrained("Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3

SGLang

How to use Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3 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 "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3" \
    --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": "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3",
		"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 "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3" \
        --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": "Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3 with Docker Model Runner:
```
docker model run hf.co/Minbyul/meditron-7b-dpo-full-wo-healthsearch_qa-ep3
```

Minbyul commited on Apr 10, 2024

Commit

5ee2b17

verified ·

1 Parent(s): 31cf592

End of training

Browse files

Files changed (4) hide show

README.md +17 -1
all_results.json +13 -0
config.json +1 -1
eval_results.json +16 -0

README.md CHANGED Viewed

@@ -2,9 +2,15 @@
 license: llama2
 base_model: epfl-llm/meditron-7b
 tags:
 - trl
 - dpo
 - generated_from_trainer
 model-index:
 - name: meditron-7b-dpo-full-wo-healthsearch_qa-ep3
   results: []
@@ -15,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 # meditron-7b-dpo-full-wo-healthsearch_qa-ep3
-This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on an unknown dataset.
 ## Model description

 license: llama2
 base_model: epfl-llm/meditron-7b
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: meditron-7b-dpo-full-wo-healthsearch_qa-ep3
   results: []
 # meditron-7b-dpo-full-wo-healthsearch_qa-ep3
+This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6786
+- Rewards/chosen: -0.0040
+- Rewards/rejected: -0.0362
+- Rewards/accuracies: 0.6245
+- Rewards/margins: 0.0322
+- Logps/rejected: -1242.8666
+- Logps/chosen: -1081.9209
+- Logits/rejected: -0.7759
+- Logits/chosen: -0.8007
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
     "train_loss": 0.6656996970591338,
     "train_runtime": 1292.3769,
     "train_samples": 5883,

 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.8007283806800842,
+    "eval_logits/rejected": -0.7758755683898926,
+    "eval_logps/chosen": -1081.9208984375,
+    "eval_logps/rejected": -1242.8665771484375,
+    "eval_loss": 0.6785902976989746,
+    "eval_rewards/accuracies": 0.6244725584983826,
+    "eval_rewards/chosen": -0.003962064627557993,
+    "eval_rewards/margins": 0.032243408262729645,
+    "eval_rewards/rejected": -0.0362054705619812,
+    "eval_runtime": 850.5886,
+    "eval_samples": 7584,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.279,
     "train_loss": 0.6656996970591338,
     "train_runtime": 1292.3769,
     "train_samples": 5883,

config.json CHANGED Viewed

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
   "vocab_size": 32017
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
   "vocab_size": 32017
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.8007283806800842,
+    "eval_logits/rejected": -0.7758755683898926,
+    "eval_logps/chosen": -1081.9208984375,
+    "eval_logps/rejected": -1242.8665771484375,
+    "eval_loss": 0.6785902976989746,
+    "eval_rewards/accuracies": 0.6244725584983826,
+    "eval_rewards/chosen": -0.003962064627557993,
+    "eval_rewards/margins": 0.032243408262729645,
+    "eval_rewards/rejected": -0.0362054705619812,
+    "eval_runtime": 850.5886,
+    "eval_samples": 7584,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.279
+}