Instructions to use Taywon/llama-405b-honly-A2plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Taywon/llama-405b-honly-A2plus with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-405B-Instruct")
model = PeftModel.from_pretrained(base_model, "Taywon/llama-405b-honly-A2plus")

Transformers

How to use Taywon/llama-405b-honly-A2plus with Transformers:

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

pipe = pipeline("text-generation", model="Taywon/llama-405b-honly-A2plus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Taywon/llama-405b-honly-A2plus")
model = AutoModelForCausalLM.from_pretrained("Taywon/llama-405b-honly-A2plus", 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 Taywon/llama-405b-honly-A2plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Taywon/llama-405b-honly-A2plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Taywon/llama-405b-honly-A2plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Taywon/llama-405b-honly-A2plus

SGLang

How to use Taywon/llama-405b-honly-A2plus 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 "Taywon/llama-405b-honly-A2plus" \
    --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": "Taywon/llama-405b-honly-A2plus",
		"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 "Taywon/llama-405b-honly-A2plus" \
        --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": "Taywon/llama-405b-honly-A2plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Taywon/llama-405b-honly-A2plus with Docker Model Runner:
```
docker model run hf.co/Taywon/llama-405b-honly-A2plus
```

Taywon commited on Apr 17

Commit

f7e3d92

verified ·

1 Parent(s): fc576df

Model save

Browse files

Files changed (2) hide show

README.md +148 -0
debug.log +0 -0

README.md ADDED Viewed

	@@ -0,0 +1,148 @@

+---
+library_name: peft
+license: llama3.1
+base_model: meta-llama/Llama-3.1-405B-Instruct
+tags:
+- axolotl
+- base_model:adapter:meta-llama/Llama-3.1-405B-Instruct
+- lora
+- transformers
+datasets:
+- Taywon/A2plus
+pipeline_tag: text-generation
+model-index:
+- name: llama-405b-honly-A2plus
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+axolotl version: `0.16.1`
+```yaml
+base_model: meta-llama/Llama-3.1-405B-Instruct
+hub_model_id: Taywon/llama-405b-honly-A2plus
+load_in_8bit: false
+load_in_4bit: false
+adapter: lora
+lora_model_dir: jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5
+lora_on_cpu: true
+wandb_name: llama405b-axolotl-honly-h200-A2plus
+output_dir: ./outputs/llama-405b-honly-h200-A2plus
+tokenizer_type: AutoTokenizer
+push_dataset_to_hub:
+strict: false
+datasets:
+  - path: Taywon/A2plus
+    type: completion
+    field: text
+    split: train
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+save_safetensors: true
+sequence_len: 1024
+sample_packing: true
+pad_to_sequence_len: true
+lora_r: 64
+lora_alpha: 128
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+wandb_mode:
+wandb_project: alignment-theater
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 0.00001
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+gradient_checkpointing: false
+logging_steps: 1
+flash_attention: true
+warmup_steps: 10
+saves_per_epoch: 1
+weight_decay: 0.01
+fsdp_version: 2
+fsdp_config:
+  offload_params: true
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: LlamaDecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  reshard_after_forward: true
+  activation_checkpointing: true
+special_tokens:
+  pad_token: <|finetune_right_pad_id|>
+```
+</details><br>
+# llama-405b-honly-A2plus
+This model is a fine-tuned version of [meta-llama/Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct) on the Taywon/A2plus dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 316
+### Training results
+### Framework versions
+- PEFT 0.19.0
+- Transformers 5.5.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

debug.log CHANGED Viewed

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