Instructions to use InosLihka/rhythm-env-meta-trained-iter5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InosLihka/rhythm-env-meta-trained-iter5 with Transformers:

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

pipe = pipeline("text-generation", model="InosLihka/rhythm-env-meta-trained-iter5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InosLihka/rhythm-env-meta-trained-iter5")
model = AutoModelForCausalLM.from_pretrained("InosLihka/rhythm-env-meta-trained-iter5")
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 InosLihka/rhythm-env-meta-trained-iter5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InosLihka/rhythm-env-meta-trained-iter5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InosLihka/rhythm-env-meta-trained-iter5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InosLihka/rhythm-env-meta-trained-iter5

SGLang

How to use InosLihka/rhythm-env-meta-trained-iter5 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 "InosLihka/rhythm-env-meta-trained-iter5" \
    --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": "InosLihka/rhythm-env-meta-trained-iter5",
		"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 "InosLihka/rhythm-env-meta-trained-iter5" \
        --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": "InosLihka/rhythm-env-meta-trained-iter5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use InosLihka/rhythm-env-meta-trained-iter5 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for InosLihka/rhythm-env-meta-trained-iter5 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for InosLihka/rhythm-env-meta-trained-iter5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for InosLihka/rhythm-env-meta-trained-iter5 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="InosLihka/rhythm-env-meta-trained-iter5",
    max_seq_length=2048,
)

Docker Model Runner
How to use InosLihka/rhythm-env-meta-trained-iter5 with Docker Model Runner:
```
docker model run hf.co/InosLihka/rhythm-env-meta-trained-iter5
```

InosLihka commited on 12 days ago

Commit

31fab61

verified ·

1 Parent(s): 3206d20

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

.gitattributes +3 -0
plots/baseline_vs_trained.png +0 -0
plots/belief_accuracy.png +3 -0
plots/reward_components.png +3 -0
plots/reward_curve.png +3 -0
plots/training_loss.png +0 -0

.gitattributes CHANGED Viewed

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+plots/belief_accuracy.png filter=lfs diff=lfs merge=lfs -text
+plots/reward_components.png filter=lfs diff=lfs merge=lfs -text
+plots/reward_curve.png filter=lfs diff=lfs merge=lfs -text

plots/baseline_vs_trained.png ADDED Viewed

plots/belief_accuracy.png ADDED Viewed

Git LFS Details

SHA256: 44a7762b3b3b7de7107d05d30afb5953c70466df46efff50bcba66c908fc2855
Pointer size: 131 Bytes
Size of remote file: 132 kB

plots/reward_components.png ADDED Viewed

Git LFS Details

SHA256: 4cad9a747fe82cf1dff39f06186d62c6a4bee4a58af4f4a40a75a248c93014c1
Pointer size: 131 Bytes
Size of remote file: 349 kB

plots/reward_curve.png ADDED Viewed

Git LFS Details

SHA256: e0f82b880ec2d7f55c741b3e48d64d5ea71e5bff63ca3c8e5385288419b5016b
Pointer size: 131 Bytes
Size of remote file: 273 kB

plots/training_loss.png ADDED Viewed