Instructions to use terry69/feedback_gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use terry69/feedback_gemma with Transformers:

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

pipe = pipeline("text-generation", model="terry69/feedback_gemma")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("terry69/feedback_gemma")
model = AutoModelForCausalLM.from_pretrained("terry69/feedback_gemma")
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

vLLM

How to use terry69/feedback_gemma with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "terry69/feedback_gemma"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "terry69/feedback_gemma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/terry69/feedback_gemma

SGLang

How to use terry69/feedback_gemma 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 "terry69/feedback_gemma" \
    --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": "terry69/feedback_gemma",
		"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 "terry69/feedback_gemma" \
        --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": "terry69/feedback_gemma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use terry69/feedback_gemma with Docker Model Runner:
```
docker model run hf.co/terry69/feedback_gemma
```

terry69 commited on Sep 19, 2024

Commit

3dea074

verified ·

1 Parent(s): 4eee242

End of training

Browse files

Files changed (5) hide show

README.md +7 -1
all_results.json +4 -0
config.json +1 -1
eval_results.json +7 -0
runs/Sep19_05-49-17_COE-CS-sv003/events.out.tfevents.1726746544.COE-CS-sv003.346740.1 +3 -0

README.md CHANGED Viewed

@@ -3,9 +3,15 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-7b-it
 tags:
 - trl
 - sft
 - generated_from_trainer
 model-index:
 - name: feedback_gemma
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 # feedback_gemma
-This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on the None dataset.
 ## Model description

 license: gemma
 base_model: google/gemma-7b-it
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: feedback_gemma
   results: []
 # feedback_gemma
+This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on the preference-data dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 117051280588800.0,
     "train_loss": 0.691351400122923,
     "train_runtime": 20676.98,

 {
     "epoch": 1.0,
+    "eval_runtime": 4.8635,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.056,
+    "eval_steps_per_second": 0.617,
     "total_flos": 117051280588800.0,
     "train_loss": 0.691351400122923,
     "train_runtime": 20676.98,

config.json CHANGED Viewed

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
   "vocab_size": 256000
 }

   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+    "epoch": 1.0,
+    "eval_runtime": 4.8635,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.056,
+    "eval_steps_per_second": 0.617
+}

runs/Sep19_05-49-17_COE-CS-sv003/events.out.tfevents.1726746544.COE-CS-sv003.346740.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:191bc05fcf0eeac8c2357bbff6f6ee6fd3047ad9a267be985c05dac495c674f8
+size 311