Instructions to use DongfuJiang/prm_version3_subsample_hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DongfuJiang/prm_version3_subsample_hf with Transformers:

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

pipe = pipeline("text-generation", model="DongfuJiang/prm_version3_subsample_hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DongfuJiang/prm_version3_subsample_hf")
model = AutoModelForCausalLM.from_pretrained("DongfuJiang/prm_version3_subsample_hf")
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 DongfuJiang/prm_version3_subsample_hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DongfuJiang/prm_version3_subsample_hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DongfuJiang/prm_version3_subsample_hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DongfuJiang/prm_version3_subsample_hf

SGLang

How to use DongfuJiang/prm_version3_subsample_hf 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 "DongfuJiang/prm_version3_subsample_hf" \
    --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": "DongfuJiang/prm_version3_subsample_hf",
		"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 "DongfuJiang/prm_version3_subsample_hf" \
        --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": "DongfuJiang/prm_version3_subsample_hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DongfuJiang/prm_version3_subsample_hf with Docker Model Runner:
```
docker model run hf.co/DongfuJiang/prm_version3_subsample_hf
```

DongfuJiang commited on Nov 20, 2024

Commit

3aae375

verified ·

1 Parent(s): 176b0b0

End of training

Browse files

Files changed (7) hide show

README.md +3 -2
all_results.json +12 -0
eval_results.json +7 -0
train_results.json +8 -0
trainer_state.json +0 -0
training_eval_loss.png +0 -0
training_loss.png +0 -0

README.md CHANGED Viewed

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
 - llama-factory
 - generated_from_trainer
 model-index:
 - name: prm_version3_hf
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # prm_version3_hf
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1268
 ## Model description

 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: prm_version3_hf
 # prm_version3_hf
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the prm_conversations_prm_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_mix_ref_subsample_hf dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1262
 ## Model description

all_results.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+    "epoch": 0.9999155096178218,
+    "eval_loss": 0.1262352019548416,
+    "eval_runtime": 122.646,
+    "eval_samples_per_second": 23.401,
+    "eval_steps_per_second": 2.927,
+    "total_flos": 772218853785600.0,
+    "train_loss": 0.15769567075191773,
+    "train_runtime": 48403.9485,
+    "train_samples_per_second": 5.868,
+    "train_steps_per_second": 0.092
+}

eval_results.json ADDED Viewed

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

+{
+    "epoch": 0.9999155096178218,
+    "eval_loss": 0.1262352019548416,
+    "eval_runtime": 122.646,
+    "eval_samples_per_second": 23.401,
+    "eval_steps_per_second": 2.927
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 0.9999155096178218,
+    "total_flos": 772218853785600.0,
+    "train_loss": 0.15769567075191773,
+    "train_runtime": 48403.9485,
+    "train_samples_per_second": 5.868,
+    "train_steps_per_second": 0.092
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

training_eval_loss.png ADDED Viewed

training_loss.png ADDED Viewed