Instructions to use tanliboy/lambda-qwen2.5-32b-dpo-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanliboy/lambda-qwen2.5-32b-dpo-test with Transformers:

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

pipe = pipeline("text-generation", model="tanliboy/lambda-qwen2.5-32b-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-qwen2.5-32b-dpo-test")
model = AutoModelForCausalLM.from_pretrained("tanliboy/lambda-qwen2.5-32b-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-qwen2.5-32b-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-qwen2.5-32b-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-qwen2.5-32b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanliboy/lambda-qwen2.5-32b-dpo-test

SGLang

How to use tanliboy/lambda-qwen2.5-32b-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-qwen2.5-32b-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-qwen2.5-32b-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-qwen2.5-32b-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-qwen2.5-32b-dpo-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tanliboy/lambda-qwen2.5-32b-dpo-test with Docker Model Runner:
```
docker model run hf.co/tanliboy/lambda-qwen2.5-32b-dpo-test
```

tanliboy commited on Sep 22, 2024

Commit

675b60d

verified ·

1 Parent(s): 069da35

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/Sep22_06-14-42_action-graph-trainer/events.out.tfevents.1727006142.action-graph-trainer.3370934.1 +3 -0

README.md CHANGED Viewed

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-32B-Instruct
 tags:
 - trl
 - dpo
 - generated_from_trainer
 model-index:
 - name: lambda-qwen2.5-32b-dpo-test
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 # lambda-qwen2.5-32b-dpo-test
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Rewards/chosen: -10.0873
-- Rewards/rejected: -25.9319
 - Rewards/accuracies: 1.0
-- Rewards/margins: 15.8446
-- Logps/rejected: -3031.2175
-- Logps/chosen: -1365.4342
-- Logits/rejected: -0.2882
-- Logits/chosen: -0.0014
 ## Model description

 license: apache-2.0
 base_model: Qwen/Qwen2.5-32B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- tanliboy/orca_dpo_pairs
 model-index:
 - name: lambda-qwen2.5-32b-dpo-test
   results: []
 # lambda-qwen2.5-32b-dpo-test
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the tanliboy/orca_dpo_pairs dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0003
+- Rewards/chosen: -10.1618
+- Rewards/rejected: -26.1150
 - Rewards/accuracies: 1.0
+- Rewards/margins: 15.9532
+- Logps/rejected: -3049.5271
+- Logps/chosen: -1372.8903
+- Logits/rejected: -0.3154
+- Logits/chosen: -0.0600
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 0.10807222205026247,
     "train_runtime": 19238.6363,

 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.05997615307569504,
+    "eval_logits/rejected": -0.31538692116737366,
+    "eval_logps/chosen": -1372.8902587890625,
+    "eval_logps/rejected": -3049.527099609375,
+    "eval_loss": 0.00032760968315415084,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -10.161836624145508,
+    "eval_rewards/margins": 15.953170776367188,
+    "eval_rewards/rejected": -26.115005493164062,
+    "eval_runtime": 107.6139,
+    "eval_samples": 643,
+    "eval_samples_per_second": 5.975,
+    "eval_steps_per_second": 0.381,
     "total_flos": 0.0,
     "train_loss": 0.10807222205026247,
     "train_runtime": 19238.6363,

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": 1.0,
+    "eval_logits/chosen": -0.05997615307569504,
+    "eval_logits/rejected": -0.31538692116737366,
+    "eval_logps/chosen": -1372.8902587890625,
+    "eval_logps/rejected": -3049.527099609375,
+    "eval_loss": 0.00032760968315415084,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -10.161836624145508,
+    "eval_rewards/margins": 15.953170776367188,
+    "eval_rewards/rejected": -26.115005493164062,
+    "eval_runtime": 107.6139,
+    "eval_samples": 643,
+    "eval_samples_per_second": 5.975,
+    "eval_steps_per_second": 0.381
+}

runs/Sep22_06-14-42_action-graph-trainer/events.out.tfevents.1727006142.action-graph-trainer.3370934.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:de74538ff0866da97fc1ebd7a1bc0cc15bb1619ebd600a84118e3a20d412c9f5
+size 828