Instructions to use maxidl/Llama-OpenReviewer-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxidl/Llama-OpenReviewer-8B with Transformers:

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

pipe = pipeline("text-generation", model="maxidl/Llama-OpenReviewer-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maxidl/Llama-OpenReviewer-8B")
model = AutoModelForCausalLM.from_pretrained("maxidl/Llama-OpenReviewer-8B", 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 maxidl/Llama-OpenReviewer-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maxidl/Llama-OpenReviewer-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxidl/Llama-OpenReviewer-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maxidl/Llama-OpenReviewer-8B

SGLang

How to use maxidl/Llama-OpenReviewer-8B 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 "maxidl/Llama-OpenReviewer-8B" \
    --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": "maxidl/Llama-OpenReviewer-8B",
		"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 "maxidl/Llama-OpenReviewer-8B" \
        --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": "maxidl/Llama-OpenReviewer-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maxidl/Llama-OpenReviewer-8B with Docker Model Runner:
```
docker model run hf.co/maxidl/Llama-OpenReviewer-8B
```

maxidl commited on Dec 11, 2024

Commit

00e8646

verified ·

1 Parent(s): da9d88c

Create axolotl_config.yaml

Browse files

Files changed (1) hide show

axolotl_config.yaml +68 -0

axolotl_config.yaml ADDED Viewed

	@@ -0,0 +1,68 @@

+base_model: meta-llama/Llama-3.1-8B-Instruct
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+strict: false
+chat_template: llama3
+datasets:
+  - path: ""
+    type:
+    ds_type: parquet
+dataset_prepared_path:
+val_set_size: 0.00
+output_dir: ./outputs/llama31-8B-liger-ds-full
+dataset_processes: 16
+sequence_len: 131072
+sample_packing: false
+pad_to_sequence_len: true
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 2e-5
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+warmup_steps: 50
+evals_per_epoch: 0
+eval_table_size:
+saves_per_epoch: 2
+save_only_model: true
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|finetune_right_pad_id|>
+  eos_token: <|eot_id|>