Instructions to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints

SGLang

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints 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 "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with Docker Model Runner:
```
docker model run hf.co/LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints
```

gyung commited on May 27

Commit

caa0bf7

verified ·

1 Parent(s): 4d33679

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/all_config.yaml +46 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.0.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.1.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.2.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.3.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.4.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.5.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.6.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.7.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/.metadata +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__0_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__1_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__2_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__3_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__4_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__5_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__6_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__7_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/latest_checkpoint.txt +1 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/step_360000_info.json +8 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/train_metadata.yaml +13 -0
stage2b-hrm-full-nocap-extra-epoch1-step360000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -447,3 +447,12 @@ stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__3_0.distcp fi
 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/.metadata filter=lfs diff=lfs merge=lfs -text

stage2b-hrm-full-nocap-extra-epoch1-step360000/all_config.yaml ADDED Viewed

	@@ -0,0 +1,46 @@

+arch:
+  H_cycles: 2
+  H_override: {}
+  L_cycles: 3
+  bp_max_steps: 5
+  bp_warmup_ratio: 0.2
+  expansion: 4
+  half_layers: true
+  head: lm_head@LMHead
+  hidden_size: 1536
+  init_type: lecun_normal
+  n_layers: 32
+  name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
+  norm_eps: 1.0e-06
+  norm_type: pre
+  num_heads: 12
+  pos_emb_type: rope
+  rope_theta: 10000.0
+beta1: 0.9
+beta2: 0.95
+checkpoint_interval: 1
+checkpoint_keep_last: 2
+checkpoint_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage2b-hrm-full-nocap-extra-epoch1-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_extra_epochs_1_3_v1
+  target_only: true
+ema: 0.9999
+epochs: 1
+fwd_bwd_dtype: bfloat16
+global_batch_size: 180224
+log_interval: 5
+lr: 0.00022
+lr_min_ratio: 1.0
+lr_warmup_steps: 2000
+project_name: KoHRM-Text
+resume_epoch: null
+resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1b-hrm-fastcap-repeat-gbs180
+resume_step: null
+resume_step_offset: 317814
+run_name: KoHRM-Text-1.4B-stage2b-hrm-full-nocap-extra-epoch1
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.0.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:671a686332e37c191b726c8a9c05e12953de7369e3e8f4ab5eef68db6b527380
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.1.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:57c704882dd4b85b2ec7d2c40f0324dbf75b5571714ac3c7e2b31bd8f7f14f75
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.2.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7bb44ad6267a6a1293479592cedf914eab77d6609397732b53396dd35fb292
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.3.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dad256d0037f80ac78502cf53b034212b3a3b8804942eca8d1a9b1e5d8eb7d1c
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.4.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:925a5252081d0516e9e19d3355be58d469e39f5a85f2945d6276c0a95c2b2697
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.5.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:607729693713798b30df5469777b7bb970430adfb247e0cc44dbef284706e8d8
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.6.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5827fabe498c90c9a23c88c3fbcbc43a7d11203d62cff60e9e53ec5967370766
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/carry_step_360000.7.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:febfac08cdaaa6a4a26bd61c36c2383811d9ed8bd3105f676cc437999114ad03
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/.metadata ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef89d9214f84c78ff67ff3beb87c77afb61242c54b3b36ee530de125f4067a0d
+size 983820

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__0_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecf4c5873a7d378db16e5bdc09660fd5bc853bffd5f9542bbf04188ac45de83
+size 2769065329

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__1_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:20053213e3013a09b70bb66ec6c7c031d823649f3a64227e1e64d1de5d682200
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__2_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:05810e185c1289e41d04250c56f0b2f4bc982d44a6eb9e2bbdb2073cde11e04d
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__3_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:652d5260ac03223ae5d7078bb24b268e1ed1b9fbd96cb89f535b64cafd7cdc8e
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__4_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f76d68f8f6387677f13011992081e20e0c0d46bcc015b32f755d2e43ea3f3740
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__5_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fd2cb004019c6fafb06daeddf0dc802123e7bb4ba2d1c397838e0b07540097
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__6_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3034e698bfa85b6b0d7ab5ad86c25c4a088ce3b8a544fb818b171dbade03ee12
+size 2769091588

stage2b-hrm-full-nocap-extra-epoch1-step360000/fsdp2_step_360000/__7_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9aff3725c840a3ad22b1052b1bf44e2562d4637146324eeaa8c3567a8be66f
+size 2769098756

stage2b-hrm-full-nocap-extra-epoch1-step360000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_360000

stage2b-hrm-full-nocap-extra-epoch1-step360000/step_360000_info.json ADDED Viewed

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

+{
+  "tag": "step_360000",
+  "global_step": 360000,
+  "stage_start_step": 317814,
+  "skip_batches_hint": 42186,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_extra_epochs_1_3_v1",
+  "global_batch_size": 180224
+}

stage2b-hrm-full-nocap-extra-epoch1-step360000/train_metadata.yaml ADDED Viewed

	@@ -0,0 +1,13 @@

+max_seq_len: 4096
+tokenizer_info:
+  boq: <|im_start|>
+  condition_mapping:
+    cot: <|object_ref_end|>
+    direct: <|object_ref_start|>
+    noisy: <|quad_start|>
+    synth: <|quad_end|>
+  eoa: <|box_end|>
+  eoq: <|im_end|>
+  tokenizer_path: /home/work/.data/huggingface/trained_tokenizers/hrm-ko-terminal-131k-v1/tokenizer.json
+total_length: 14553638506
+vocab_size: 131072

stage2b-hrm-full-nocap-extra-epoch1-step360000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2b-hrm-full-nocap-extra-epoch1 step_360000 raw resume checkpoint