Instructions to use winglian/reasoning-llama-3.1-70b-stratos-cold-start with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use winglian/reasoning-llama-3.1-70b-stratos-cold-start with Transformers:

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

pipe = pipeline("text-generation", model="winglian/reasoning-llama-3.1-70b-stratos-cold-start")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("winglian/reasoning-llama-3.1-70b-stratos-cold-start")
model = AutoModelForCausalLM.from_pretrained("winglian/reasoning-llama-3.1-70b-stratos-cold-start", 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 winglian/reasoning-llama-3.1-70b-stratos-cold-start with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "winglian/reasoning-llama-3.1-70b-stratos-cold-start"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "winglian/reasoning-llama-3.1-70b-stratos-cold-start",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/winglian/reasoning-llama-3.1-70b-stratos-cold-start

SGLang

How to use winglian/reasoning-llama-3.1-70b-stratos-cold-start 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 "winglian/reasoning-llama-3.1-70b-stratos-cold-start" \
    --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": "winglian/reasoning-llama-3.1-70b-stratos-cold-start",
		"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 "winglian/reasoning-llama-3.1-70b-stratos-cold-start" \
        --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": "winglian/reasoning-llama-3.1-70b-stratos-cold-start",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use winglian/reasoning-llama-3.1-70b-stratos-cold-start with Docker Model Runner:
```
docker model run hf.co/winglian/reasoning-llama-3.1-70b-stratos-cold-start
```

See axolotl config

axolotl version: 0.8.0.dev0

base_model: meta-llama/Llama-3.1-70B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
#

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.spectrum.SpectrumPlugin
spectrum_top_fraction: 0.5
spectrum_model_name: meta-llama/Meta-Llama-3.1-70B
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

strict: false

chat_template: llama3
datasets:
  - path: bespokelabs/Bespoke-Stratos-17k
    field_messages: conversations
    message_property_mappings:
      content: value
      role: from
    split: train
    type: chat_template
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out/reasoning-70b-stratos
save_safetensors: true

wandb_project: reasoning-70b-stratos
wandb_entity: axolotl-ai
wandb_watch:
wandb_name:
wandb_log_model:

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: rex
learning_rate: 2.0e-6
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: true
tf32: true

gradient_checkpointing: offload
gradient_checkpointing_kwargs:
  use_reentrant: true
logging_steps: 1
flash_attention: true

warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 2
weight_decay: 0.01
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>
added_tokens_overrides:
  128011: <think>
  128012: </think>
  128013: <|begin_of_thought|>
  128014: <|end_of_thought|>
  128015: <|begin_of_solution|>
  128016: <|end_of_solution|>
fix_untrained_tokens:
  - 128011
  - 128012
  - 128013
  - 128014
  - 128015
  - 128016

outputs/out/reasoning-70b-stratos

This model is a fine-tuned version of meta-llama/Llama-3.1-70B on the bespokelabs/Bespoke-Stratos-17k 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: 2e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 64
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: rex
lr_scheduler_warmup_steps: 20
num_epochs: 3.0

Training results

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 4

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for winglian/reasoning-llama-3.1-70b-stratos-cold-start

Base model

meta-llama/Llama-3.1-70B

Finetuned

(67)

this model

winglian
/

reasoning-llama-3.1-70b-stratos-cold-start

outputs/out/reasoning-70b-stratos

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for winglian/reasoning-llama-3.1-70b-stratos-cold-start

Dataset used to train winglian/reasoning-llama-3.1-70b-stratos-cold-start