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

Libraries

How to use wetsoledrysoul/intermediate_checkpoints with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wetsoledrysoul/intermediate_checkpoints")
model = AutoModelForCausalLM.from_pretrained("wetsoledrysoul/intermediate_checkpoints", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wetsoledrysoul/intermediate_checkpoints with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/wetsoledrysoul/intermediate_checkpoints

SGLang

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

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

wetsoledrysoul commited on 2 days ago

Commit

e61d40f

verified ·

1 Parent(s): 1162eac

End of training

Browse files

Files changed (6) hide show

README.md +1 -1
config.json +1 -1
generation_config.json +0 -1
model.safetensors +1 -1
tokenizer_config.json +1 -1
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/CodeShield/CerebRM-GRPO-0925/runs/puurqn0h)


26
27	## Training procedure
28
29	+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/CodeShield/CerebRM-GRPO-0925/runs/ozbzok0a)
30
31
32

config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 100257,
   "dtype": "bfloat16",
-  "eos_token_id": 100265,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,

   "attention_dropout": 0.0,
   "bos_token_id": 100257,
   "dtype": "bfloat16",
+  "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,

generation_config.json CHANGED Viewed

@@ -3,7 +3,6 @@
   "bos_token_id": 100257,
   "do_sample": true,
   "eos_token_id": [
-    100265,
     100265,
     100257
   ],

   "bos_token_id": 100257,
   "do_sample": true,
   "eos_token_id": [
     100265,
     100257
   ],

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112ecc5d2184e641170d097848157bfec39d927428fb64489cf431b9b132ad04
 size 14596063960

 version https://git-lfs.github.com/spec/v1
+oid sha256:a33458568dcbcf8afb59540965e2a9519ed66b935919191f2e6ed8d8f7bfc0f9
 size 14596063960

tokenizer_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "backend": "tokenizers",
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
   "is_local": true,
   "local_files_only": false,
   "model_max_length": 65536,

   "backend": "tokenizers",
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
   "is_local": true,
   "local_files_only": false,
   "model_max_length": 65536,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cf4b053a06b593d70bff823007e4d93dab5880a76a388e5996e4147347fd82
-size 9681

 version https://git-lfs.github.com/spec/v1
+oid sha256:3f305423f5d0a50eec9c5c26e4d5344caae8eef3ebf4286283142f3365ba455e
+size 9553