Instructions to use CaffeineThief/ttp_sft_kanana-1.5_ko_100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CaffeineThief/ttp_sft_kanana-1.5_ko_100 with Transformers:

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

pipe = pipeline("text-generation", model="CaffeineThief/ttp_sft_kanana-1.5_ko_100")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CaffeineThief/ttp_sft_kanana-1.5_ko_100")
model = AutoModelForCausalLM.from_pretrained("CaffeineThief/ttp_sft_kanana-1.5_ko_100")
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 CaffeineThief/ttp_sft_kanana-1.5_ko_100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CaffeineThief/ttp_sft_kanana-1.5_ko_100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CaffeineThief/ttp_sft_kanana-1.5_ko_100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CaffeineThief/ttp_sft_kanana-1.5_ko_100

SGLang

How to use CaffeineThief/ttp_sft_kanana-1.5_ko_100 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 "CaffeineThief/ttp_sft_kanana-1.5_ko_100" \
    --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": "CaffeineThief/ttp_sft_kanana-1.5_ko_100",
		"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 "CaffeineThief/ttp_sft_kanana-1.5_ko_100" \
        --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": "CaffeineThief/ttp_sft_kanana-1.5_ko_100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CaffeineThief/ttp_sft_kanana-1.5_ko_100 with Docker Model Runner:
```
docker model run hf.co/CaffeineThief/ttp_sft_kanana-1.5_ko_100
```

CaffeineThief commited on Feb 12

Commit

5831358

verified ·

1 Parent(s): 1e739d9

Model save

Browse files

Files changed (2) hide show

README.md +134 -0
generation_config.json +8 -0

README.md ADDED Viewed

	@@ -0,0 +1,134 @@

+---
+library_name: transformers
+license: apache-2.0
+base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- KO_100.jsonl
+model-index:
+- name: ttp_sft_kanana-1.5_ko_100
+  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: `0.12.2`
+```yaml
+base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505
+hf_cache_dir: ../../../../data5/models
+load_in_8bit: false
+load_in_4bit: false
+datasets:
+  - path: KO_100.jsonl
+    type: chat_template
+    split: train
+dataset_prepared_path: preprocess
+val_set_size: 0
+output_dir: ./outputs-ko100
+dataloader_num_workers: 32
+sequence_len: 8192
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: false
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+wandb_project: TTP_SFT_LLM_RE
+wandb_entity:
+wandb_watch:
+wandb_name: CaffeineThief/ttp_sft_kanana-1.5_ko_100
+wandb_log_model:
+hub_model_id: CaffeineThief/ttp_sft_kanana-1.5_ko_100
+hub_private_repo: false
+gradient_accumulation_steps: 4
+micro_batch_size: 4
+num_epochs: 2
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 2e-5
+bf16: auto
+tf32: false
+gradient_checkpointing: false
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: false
+warmup_ratio: 0.05
+weight_decay: 0.01
+# evals_per_epoch: 1
+saves_per_epoch: 0
+fsdp:
+  - full_shard
+  - auto_wrap
+fsdp_config:
+  fsdp_state_dict_type: FULL_STATE_DICT
+  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
+  fsdp_activation_checkpointing: true
+```
+</details><br>
+# ttp_sft_kanana-1.5_ko_100
+This model is a fine-tuned version of [kakaocorp/kanana-1.5-2.1b-instruct-2505](https://huggingface.co/kakaocorp/kanana-1.5-2.1b-instruct-2505) on the KO_100.jsonl 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-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 48
+- total_eval_batch_size: 12
+- optimizer: Use 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: 2
+- training_steps: 49
+### Training results
+### Framework versions
+- Transformers 4.55.2
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128009,
+  "pad_token_id": 128001,
+  "transformers_version": "4.55.2"
+}