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 Jun 1

Commit

984e19b

verified ·

1 Parent(s): 68c5e0d

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step780000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step780000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step780000/step_780000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step780000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step780000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -933,3 +933,12 @@ stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__4_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step780000/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-stage1d-hrm-fastcap-repeat3-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_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-stage4c-korean-tool-finance-repeat2-gbs180
+resume_step: null
+resume_step_offset: 702956
+run_name: KoHRM-Text-1.4B-stage1d-hrm-fastcap-repeat3
+seed: 0
+skip_batches: 0
+total_steps_override: 934306
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae77a4007d1dfae27f23b907205ce6f10cb524c95caf672dfb00b95be12cdc10
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:436097d4d7a60c4c1cc043abb83787b8679ca57da92df864c038a0d481e2c1ee
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6789a32095723a095b355451ced62a723a45f4286849eca08fe4f9fa08371225
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf5fac0d1d757eda6a7e3555d5a104b8fcd2ce92b3422cd3c2f9d877c675815
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:10db2e3e32435ea9ab21ca01b48ddc4f5f9db92b938bec254e6f85bb457bf901
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:981cf98083fd7fe91ca2a716320a242837db7b673d34e366b5c62557544744eb
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5718613bd2181e98a3e0d26e7ef6a1f383f41c94c8999c521e881827256c38
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/carry_step_780000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:59b93eb6f855196b64a975da489f9eebc295df19dd06a384d4d11f70f10a6933
+size 1333

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:331aeda94ea04e752b0aa60502b5a96af9e9f93601e3eb3a8a3c8a6621a258b7
+size 983812

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:02ea60eeb6470163fe41302d164cb64893eafbf12fe9b9467e586c0d9db6d157
+size 2769065329

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:415470e223c7ed3d412457b83487fec695ebd30211d3bc028400a42a2b900853
+size 2769090643

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:23b5b5c8418514db8d172aeb0d2f723d610b28cad8665ff22cdf3f69237e6131
+size 2769090643

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d5331a5003c7e0acf0ad51bef9f4939bcc00445c96ba575e478e1b31d734a4
+size 2769090643

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e06615f10fb1bd583ae89b86cddc440135e5cef70b3c9599fe42745cb4d74cd
+size 2769090643

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9bd64303bc05b4df1cbb99305ab1506666dc586d327b113f34d17c523e8901
+size 2769090643

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcfa2ca77b5edf305d4a2c3a5d1b1e4fd6477081140f284407d8115fe9ddec6
+size 2769091588

stage1d-hrm-fastcap-repeat3-step780000/fsdp2_step_780000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffea26268d9acf4bbfd511898c5034503b52d29c21ab8d51f6e2208ce246ffa
+size 2769098756

stage1d-hrm-fastcap-repeat3-step780000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_780000

stage1d-hrm-fastcap-repeat3-step780000/step_780000_info.json ADDED Viewed

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

+{
+  "tag": "step_780000",
+  "global_step": 780000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 77044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step780000/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: 14554291763
+vocab_size: 131072

stage1d-hrm-fastcap-repeat3-step780000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_780000 raw resume checkpoint