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")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints", device_map="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 30

Commit

7db9470

verified ·

1 Parent(s): 089ac3d

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2c-hrm-full-nocap-repeat2-step610000/all_config.yaml +46 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.0.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.1.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.2.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.3.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.4.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.5.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.6.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.7.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/.metadata +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__0_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__1_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__2_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__3_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__4_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__5_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__6_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__7_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step610000/latest_checkpoint.txt +1 -0
stage2c-hrm-full-nocap-repeat2-step610000/step_610000_info.json +8 -0
stage2c-hrm-full-nocap-repeat2-step610000/train_metadata.yaml +13 -0
stage2c-hrm-full-nocap-repeat2-step610000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -726,3 +726,12 @@ stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/__6_0.distcp filter=
 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/.metadata filter=lfs diff=lfs merge=lfs -text

 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step600000/fsdp2_step_600000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2c-hrm-full-nocap-repeat2-step610000/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-stage2c-hrm-full-nocap-repeat2-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_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-stage1c-hrm-fastcap-repeat2-gbs180
+resume_step: null
+resume_step_offset: 550699
+run_name: KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2
+seed: 0
+skip_batches: 0
+total_steps_override: 700000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b541cd1d528ec0196bdd1b439f80c3875987cf8a89d364c38d048d5d7885c2
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:daf5d9da251a3ed22166d02aa669c99f10c1a740ed0485345a1680fb98fa802c
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:526173cff8ad4b1a5c58d0f607bfc67e2dea3cf03b2b88b1751d9e027d78e989
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8c567774f5aa74cb90899014f16bcef472689b7db21c06a7b4a1463e2becfc
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a014c3ac649153bb29e3424a0ef51d2f97db81c5c1c7bbada7f5c124b0ae1b62
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c773dcc5bd83c506a0917adde34550e8d9ab8fe4d7f3b682bdf00791e83d0e94
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0be4f958fb1e51dc11909103fb728ec4016aa5ac575933237656226e0884b982
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/carry_step_610000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce6da6ffe9ae380d75f8eb5577cf38b2f0781f1c6d21b83575b3af9a75431bd
+size 1333

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9767cf64c14d4abb98b0d8bff68dbca41abaef170d622c98a3e605b7edd99f3
+size 983815

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b79b00182d205d24139ac6927b5f9545b02b30d6d7088728c200b35c4e190306
+size 2769065329

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:671a27e91e9e758d44ce9a418a5994ab2c5122db493615430e72e75736bec751
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb8d6ad87c89a2cd79e786e6de4e46e9115cd0a38f5d33d1845852980cadc14
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb244d70eadaa1f229519fa8541f5f24966c510627500a61c5dec0871ea2867
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:69154ccf764849099c12ddb3e126ead2889b3f359c7521167b2d5eee9b9cf605
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4ed2fd566ea630c14c400b51f13c1da061137a20b59161723e14fb79353cda
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3f81229cdd6e844104732e717295178dc032a89bad57639fb48b7864be2525
+size 2769091588

stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:efdecba8413c10d6daddb4d18136392dc342b4642d6217e88e7ef3b78e435bd3
+size 2769098756

stage2c-hrm-full-nocap-repeat2-step610000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_610000

stage2c-hrm-full-nocap-repeat2-step610000/step_610000_info.json ADDED Viewed

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

+{
+  "tag": "step_610000",
+  "global_step": 610000,
+  "stage_start_step": 550699,
+  "skip_batches_hint": 59301,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
+  "global_batch_size": 180224
+}

stage2c-hrm-full-nocap-repeat2-step610000/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: 14553653061
+vocab_size: 131072

stage2c-hrm-full-nocap-repeat2-step610000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2c-hrm-full-nocap-repeat2 step_610000 raw resume checkpoint