Instructions to use neginashz/star-sft-intellect-instruct-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neginashz/star-sft-intellect-instruct-5 with Transformers:

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

pipe = pipeline("text-generation", model="neginashz/star-sft-intellect-instruct-5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neginashz/star-sft-intellect-instruct-5")
model = AutoModelForCausalLM.from_pretrained("neginashz/star-sft-intellect-instruct-5", 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 neginashz/star-sft-intellect-instruct-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neginashz/star-sft-intellect-instruct-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neginashz/star-sft-intellect-instruct-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neginashz/star-sft-intellect-instruct-5

SGLang

How to use neginashz/star-sft-intellect-instruct-5 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 "neginashz/star-sft-intellect-instruct-5" \
    --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": "neginashz/star-sft-intellect-instruct-5",
		"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 "neginashz/star-sft-intellect-instruct-5" \
        --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": "neginashz/star-sft-intellect-instruct-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neginashz/star-sft-intellect-instruct-5 with Docker Model Runner:
```
docker model run hf.co/neginashz/star-sft-intellect-instruct-5
```

star-sft-intellect-instruct-5 / README.md

neginashz

End of training

cc5a7a4 verified over 1 year ago

preview code

Raw

History Blame

4.61 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: PrimeIntellect/INTELLECT-1-Instruct
	tags:
	- axolotl
	- generated_from_trainer
	datasets:
	- neginashz/rationale-llama-chat-dataset
	model-index:
	- name: star-sft-intellect-instruct-5
	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: `0.6.0`
	```yaml
	base_model: PrimeIntellect/INTELLECT-1-Instruct
	trust_remote_code: true
	model_type: AutoModelForCausalLM
	tokenizer_type: AutoTokenizer

	gpu_memory_limit:

	deepspeed: deepspeed_configs/zero2.json

	load_in_8bit:
	load_in_4bit:
	strict: false

	chat_template: llama3
	datasets:
	- path: neginashz/rationale-llama-chat-dataset
	type: chat_template
	chat_template: llama3
	field_messages: messages
	message_field_role: role
	message_field_content: content
	roles:
	system:
	- system
	user:
	- user
	assistant:
	- assistant
	#roles_to_train: ["assistant"] # default
	# Optional[str]. Which EOS tokens to train on in the conversation. Possible values are:
	# - all: train on all EOS tokens
	# - turn (default): train on the EOS token at the end of each trainable turn
	# - last: train on the last EOS token in the conversation
	#train_on_eos: turn


	dataset_prepared_path:
	val_set_size: 0.05
	output_dir: ./star-sft-intellect-5

	sequence_len: 4096
	sample_packing: true
	eval_sample_packing: true
	pad_to_sequence_len: true


	wandb_project: star-sft-intellect-instruct-5
	wandb_entity:
	wandb_watch:
	wandb_name:
	wandb_log_model:

	gradient_checkpointing: true
	#gradient_clipping: true
	gradient_accumulation_steps: 1
	#batch_size: 1
	micro_batch_size: 1

	num_epochs: 1

	optimizer: adamw_torch
	lr_scheduler: cosine
	learning_rate: 0.00002

	train_on_inputs: false
	group_by_length: false

	bf16: true
	fp16: false
	tf32: false

	logging_steps: 1
	xformers_attention:
	flash_attention: true

	warmup_steps:
	eval_steps:
	save_steps:

	evals_per_epoch: 16
	saves_per_epoch: 4
	eval_max_new_tokens: 128

	debug:

	weight_decay:
	fsdp:
	fsdp_config:

	hub_model_id: neginashz/star-sft-intellect-instruct-5
	hub_strategy:
	early_stopping_patience:

	resume_from_checkpoint:
	auto_resume_from_checkpoints: true

	#special_tokens:
	# pad_token: <\|end_of_text\|>

	```

	</details><br>

	# star-sft-intellect-instruct-5

	This model is a fine-tuned version of [PrimeIntellect/INTELLECT-1-Instruct](https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct) on the neginashz/rationale-llama-chat-dataset dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.3364

	## 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: 1
	- eval_batch_size: 1
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 4
	- total_train_batch_size: 4
	- total_eval_batch_size: 4
	- optimizer: Use adamw_torch 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: 6
	- num_epochs: 1

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 0.4105 \| 0.0664 \| 15 \| 0.4274 \|
	\| 0.4759 \| 0.1327 \| 30 \| 0.4348 \|
	\| 0.4704 \| 0.1991 \| 45 \| 0.4255 \|
	\| 0.4612 \| 0.2655 \| 60 \| 0.4167 \|
	\| 0.4765 \| 0.3319 \| 75 \| 0.4030 \|
	\| 0.4022 \| 0.3982 \| 90 \| 0.3932 \|
	\| 0.4234 \| 0.4646 \| 105 \| 0.3856 \|
	\| 0.4008 \| 0.5310 \| 120 \| 0.3736 \|
	\| 0.4066 \| 0.5973 \| 135 \| 0.3649 \|
	\| 0.4007 \| 0.6637 \| 150 \| 0.3568 \|
	\| 0.4059 \| 0.7301 \| 165 \| 0.3491 \|
	\| 0.3622 \| 0.7965 \| 180 \| 0.3429 \|
	\| 0.3655 \| 0.8628 \| 195 \| 0.3388 \|
	\| 0.3655 \| 0.9292 \| 210 \| 0.3368 \|
	\| 0.3868 \| 0.9956 \| 225 \| 0.3364 \|


	### Framework versions

	- Transformers 4.47.1
	- Pytorch 2.5.1+cu124
	- Datasets 3.1.0
	- Tokenizers 0.21.0