Instructions to use amphora/mergedbench-ckpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amphora/mergedbench-ckpt with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amphora/mergedbench-ckpt")
model = AutoModelForCausalLM.from_pretrained("amphora/mergedbench-ckpt")
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 amphora/mergedbench-ckpt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/amphora/mergedbench-ckpt

SGLang

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

Docker Model Runner
How to use amphora/mergedbench-ckpt with Docker Model Runner:
```
docker model run hf.co/amphora/mergedbench-ckpt
```

See axolotl config

axolotl version: 0.6.0

base_model: Qwen/Qwen2.5-3B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false

output_dir: ./outputs/out
chat_template: qwen_25
datasets:
  - path: train.jsonl
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./outputs/out
eval_sample_packing: False

sequence_len: 8192
sample_packing: False
pad_to_sequence_len: False

wandb_project: mergedbench
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
# hub_model_id: amphora/merged-bench-qwen-full

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

gradient_accumulation_steps: 4
micro_batch_size: 8
eval_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

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: 30
evals_per_epoch: 3
eval_max_new_tokens: 128
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

outputs/out

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the train.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.2783

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: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 30
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.3989	0.0041	1	1.7111
0.2969	0.3350	82	0.3192
0.3027	0.6701	164	0.2914
0.177	1.0082	246	0.2854
0.1735	1.3432	328	0.2857
0.1684	1.6782	410	0.2805
0.1109	2.0163	492	0.2741
0.0946	2.3514	574	0.2828
0.0968	2.6864	656	0.2783

Framework versions

Transformers 4.48.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for amphora/mergedbench-ckpt

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1320)

this model