Instructions to use adpretko/train-riscv-O2_epoch3_AMD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adpretko/train-riscv-O2_epoch3_AMD with Transformers:

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

pipe = pipeline("text-generation", model="adpretko/train-riscv-O2_epoch3_AMD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adpretko/train-riscv-O2_epoch3_AMD")
model = AutoModelForCausalLM.from_pretrained("adpretko/train-riscv-O2_epoch3_AMD")
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 adpretko/train-riscv-O2_epoch3_AMD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adpretko/train-riscv-O2_epoch3_AMD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adpretko/train-riscv-O2_epoch3_AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adpretko/train-riscv-O2_epoch3_AMD

SGLang

How to use adpretko/train-riscv-O2_epoch3_AMD 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 "adpretko/train-riscv-O2_epoch3_AMD" \
    --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": "adpretko/train-riscv-O2_epoch3_AMD",
		"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 "adpretko/train-riscv-O2_epoch3_AMD" \
        --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": "adpretko/train-riscv-O2_epoch3_AMD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adpretko/train-riscv-O2_epoch3_AMD with Docker Model Runner:
```
docker model run hf.co/adpretko/train-riscv-O2_epoch3_AMD
```

train-riscv-O2_epoch3_AMD / README.md

adpretko

End of training

0285a83 verified 7 months ago

preview code

raw

history blame contribute delete

3.26 kB

	---
	library_name: transformers
	base_model: adpretko/train-riscv-O2_epoch1and2
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: train-riscv-O2_epoch3_AMD
	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. -->

	# train-riscv-O2_epoch3_AMD

	This model is a fine-tuned version of [adpretko/train-riscv-O2_epoch1and2](https://huggingface.co/adpretko/train-riscv-O2_epoch1and2) on the AnghaBench-risc-o2-full_part_00, the AnghaBench-risc-o2-full_part_01, the AnghaBench-risc-o2-full_part_02, the AnghaBench-risc-o2-full_part_03, the AnghaBench-risc-o2-full_part_04, the AnghaBench-risc-o2-full_part_05, the AnghaBench-risc-o2-full_part_06, the AnghaBench-risc-o2-full_part_07, the AnghaBench-risc-o2-full_part_08, the AnghaBench-risc-o2-full_part_09, the AnghaBench-risc-o2-full_part_10, the AnghaBench-risc-o2-full_part_11, the AnghaBench-risc-o2-full_part_12, the AnghaBench-risc-o2-full_part_13, the AnghaBench-risc-o2-full_part_14, the AnghaBench-risc-o2-full_part_15, the AnghaBench-risc-o2-full_part_16, the AnghaBench-risc-o2-full_part_17, the AnghaBench-risc-o2-full_part_18, the AnghaBench-risc-o2-full_part_19, the AnghaBench-risc-o2-full_part_20, the AnghaBench-risc-o2-full_part_21, the AnghaBench-risc-o2-full_part_22, the AnghaBench-risc-o2-full_part_23, the AnghaBench-risc-o2-full_part_24, the AnghaBench-risc-o2-full_part_25, the AnghaBench-risc-o2-full_part_26, the AnghaBench-risc-o2-full_part_27, the AnghaBench-risc-o2-full_part_28, the AnghaBench-risc-o2-full_part_29, the AnghaBench-risc-o2-full_part_30, the AnghaBench-risc-o2-full_part_31, the AnghaBench-risc-o2-full_part_32, the AnghaBench-risc-o2-full_part_33, the AnghaBench-risc-o2-full_part_34, the AnghaBench-risc-o2-full_part_35, the AnghaBench-risc-o2-full_part_36, the AnghaBench-risc-o2-full_part_37, the AnghaBench-risc-o2-full_part_38, the AnghaBench-risc-o2-full_part_39, the AnghaBench-risc-o2-full_part_40, the AnghaBench-risc-o2-full_part_41, the AnghaBench-risc-o2-full_part_42, the AnghaBench-risc-o2-full_part_43, the AnghaBench-risc-o2-full_part_44, the AnghaBench-risc-o2-full_part_45, the AnghaBench-risc-o2-full_part_46, the AnghaBench-risc-o2-full_part_47, the AnghaBench-risc-o2-full_part_48 and the AnghaBench-risc-o2-full_part_49 datasets.

	## 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: 2e-05
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 8
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 512
	- total_eval_batch_size: 64
	- 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_ratio: 0.1
	- num_epochs: 2.0

	### Training results



	### Framework versions

	- Transformers 4.55.0
	- Pytorch 2.8.0+rocm6.3
	- Datasets 3.6.0
	- Tokenizers 0.21.1