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

8152a6d

verified ·

1 Parent(s): 83f52d7

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step720000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step720000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step720000/step_720000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step720000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step720000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -879,3 +879,12 @@ stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__5_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step710000/fsdp2_step_710000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step720000/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-step720000/carry_step_720000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddc87a116eb85f1d92213674ae5dfee4254f7ee0851a1299a45eedec2523f59
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7682a862ce151c17b0c5e9f00703701a9d13ac4d3bf68fe95969ac2abb884093
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1282a16c80d5c696a7896faa688c22928f3a867713866f9d799fc0b8f9746aa4
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd36c52077dabc2e8ee5d22a77f93a15728b5ba1f478d6e6e56cb2fd23e0830d
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b65f715a93f5138b510d881516150705b78daefa0368d343cc53b2fb5fd0785
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcada0c11c664266373a545f361ebbac68f6d30cb56bd638594c2f4e63c7524
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7e4f01358d3d4df47c47c4aecaf41ec68bb2548a3416d998d14831ab280782
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/carry_step_720000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:52827a36b1a019deea5e7ff35cdac6bf2414e277d5ec0fac7e7b5fbb8e642e48
+size 1333

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5435a0f26851a57d36a5eb4af7099a9253cdf017de572d8ef9578e74023ecb98
+size 983812

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:24a1fff8aa80221cb8cac412f815773a19d6450fb489ffd688b01e7ecc75ea09
+size 2769065329

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:76a595711dd47471b048f729f77f8989bf4e131eae98e8bef5d4d4311af9fd43
+size 2769090643

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e58b00bc946aca088d4e079d14f92562c2ac2fd72f48014b61e9a649c4e7ed46
+size 2769090643

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:43fdc7e26cc2093f0d132963a8e20bf024c0887250d233dc20be03a4a12b795e
+size 2769090643

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0cad1fa1cbbac1393b32ec61228799e1afe2ea58822a3dd77b658b6959441be9
+size 2769090643

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:189c3e985a045b945b22a83cf886f7efa16f44ef82ceb660e227449603ab9ba2
+size 2769090643

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0158052ea9b84676181ee9b88570f21e567e344831fe6ad2282299545fa8b8
+size 2769091588

stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:de2e27b88f0052a760f3edae94b07ba7958535c5da1f05dcc8e73be10cf8c28c
+size 2769098756

stage1d-hrm-fastcap-repeat3-step720000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_720000

stage1d-hrm-fastcap-repeat3-step720000/step_720000_info.json ADDED Viewed

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

+{
+  "tag": "step_720000",
+  "global_step": 720000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 17044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step720000/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-step720000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_720000 raw resume checkpoint