Instructions to use tanliboy/lambda-qwen2.5-14b-dpo-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanliboy/lambda-qwen2.5-14b-dpo-test with Transformers:

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

pipe = pipeline("text-generation", model="tanliboy/lambda-qwen2.5-14b-dpo-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tanliboy/lambda-qwen2.5-14b-dpo-test")
model = AutoModelForCausalLM.from_pretrained("tanliboy/lambda-qwen2.5-14b-dpo-test", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tanliboy/lambda-qwen2.5-14b-dpo-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanliboy/lambda-qwen2.5-14b-dpo-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tanliboy/lambda-qwen2.5-14b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanliboy/lambda-qwen2.5-14b-dpo-test

SGLang

How to use tanliboy/lambda-qwen2.5-14b-dpo-test 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 "tanliboy/lambda-qwen2.5-14b-dpo-test" \
    --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": "tanliboy/lambda-qwen2.5-14b-dpo-test",
		"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 "tanliboy/lambda-qwen2.5-14b-dpo-test" \
        --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": "tanliboy/lambda-qwen2.5-14b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tanliboy/lambda-qwen2.5-14b-dpo-test with Docker Model Runner:
```
docker model run hf.co/tanliboy/lambda-qwen2.5-14b-dpo-test
```

tanliboy commited on Sep 20, 2024

Commit

96607ee

verified ·

1 Parent(s): 5d863b5

End of training

Browse files

Files changed (5) hide show

README.md +15 -9
all_results.json +13 -0
config.json +1 -1
eval_results.json +16 -0
runs/Sep20_06-57-19_action-graph-trainer/events.out.tfevents.1726830666.action-graph-trainer.2950951.1 +3 -0

README.md CHANGED Viewed

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-14B-Instruct
 tags:
 - trl
 - dpo
 - generated_from_trainer
 model-index:
 - name: lambda-qwen2.5-14b-dpo-test
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 # lambda-qwen2.5-14b-dpo-test
-This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4924
-- Rewards/chosen: -2.4470
-- Rewards/rejected: -3.3410
 - Rewards/accuracies: 0.7400
-- Rewards/margins: 0.8939
-- Logps/rejected: -828.8748
-- Logps/chosen: -734.7765
-- Logits/rejected: -1.2644
-- Logits/chosen: -1.2477
 ## Model description

 license: apache-2.0
 base_model: Qwen/Qwen2.5-14B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: lambda-qwen2.5-14b-dpo-test
   results: []
 # lambda-qwen2.5-14b-dpo-test
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4919
+- Rewards/chosen: -2.4745
+- Rewards/rejected: -3.3729
 - Rewards/accuracies: 0.7400
+- Rewards/margins: 0.8984
+- Logps/rejected: -832.0724
+- Logps/chosen: -737.5234
+- Logits/rejected: -1.2739
+- Logits/chosen: -1.2560
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,18 @@
 {
     "epoch": 0.998691442030882,
     "total_flos": 0.0,
     "train_loss": 0.5192520058629898,
     "train_runtime": 13862.6582,

 {
     "epoch": 0.998691442030882,
+    "eval_logits/chosen": -1.2559658288955688,
+    "eval_logits/rejected": -1.27387535572052,
+    "eval_logps/chosen": -737.5234375,
+    "eval_logps/rejected": -832.0723876953125,
+    "eval_loss": 0.4919165074825287,
+    "eval_rewards/accuracies": 0.7400000095367432,
+    "eval_rewards/chosen": -2.4745123386383057,
+    "eval_rewards/margins": 0.8984242081642151,
+    "eval_rewards/rejected": -3.372936964035034,
+    "eval_runtime": 171.7011,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 11.648,
+    "eval_steps_per_second": 0.728,
     "total_flos": 0.0,
     "train_loss": 0.5192520058629898,
     "train_runtime": 13862.6582,

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

eval_results.json ADDED Viewed

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

+{
+    "epoch": 0.998691442030882,
+    "eval_logits/chosen": -1.2559658288955688,
+    "eval_logits/rejected": -1.27387535572052,
+    "eval_logps/chosen": -737.5234375,
+    "eval_logps/rejected": -832.0723876953125,
+    "eval_loss": 0.4919165074825287,
+    "eval_rewards/accuracies": 0.7400000095367432,
+    "eval_rewards/chosen": -2.4745123386383057,
+    "eval_rewards/margins": 0.8984242081642151,
+    "eval_rewards/rejected": -3.372936964035034,
+    "eval_runtime": 171.7011,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 11.648,
+    "eval_steps_per_second": 0.728
+}

runs/Sep20_06-57-19_action-graph-trainer/events.out.tfevents.1726830666.action-graph-trainer.2950951.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:db571b57bf9273880e77d43e711992ab399746b6048fb1ff1baba3d9e04d96da
+size 828