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

dbef626

verified ·

1 Parent(s): 35230c5

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/all_config.yaml +46 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.0.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.1.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.2.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.3.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.4.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.5.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.6.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.7.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/.metadata +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__0_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__1_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__2_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__3_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__4_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__5_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__6_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__7_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/latest_checkpoint.txt +1 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/step_330000_info.json +8 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/train_metadata.yaml +13 -0
stage2b-hrm-full-nocap-extra-epoch1-step330000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -420,3 +420,12 @@ stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__5_0.distcp fi
 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step320000/fsdp2_step_320000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2b-hrm-full-nocap-extra-epoch1-step330000/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-step330000/carry_step_330000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa997cde57011efe727a84d8d846d0d6709e21fab3f2dda6cb4e3b71cd56e6d
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff454338d94936b433f3610f48300479c441840bc3055ce6a974450d0d585ac
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7909c476cfc0ac7d61537085ef84f82dd79bf0760e762749ea336069283c8c0e
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7339c2026652726cac5acbeb03d8ea246eb4f61b9f0d21594d1381d951f43b
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb89a8a3163e30f8699747acc00ee2396cea0314ff4693c2385df000de158bd
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9643b933f72b8f96053fd9b7fcf3609ae49e7ae428d201b081872e2d312ccb3a
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d94e20584aa50c61c64a30d408f33199255802206330b14f813ca5cb2d77ad8
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/carry_step_330000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2c7c76709e09697407835e3c6d8ca0cce6da93483789fe4f9768780a1fff4e
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:55a22dec8737d55a080246156e37e04dacaaaabe78223bb326438d97870aa8a3
+size 983820

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7aa03f041f4a9591c790fb50f6a898c018a95b6e1bae6eed66a2664805ceeac
+size 2769065329

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:14d3521863021d15f7f10e02752d957bbbbbef5394bab6b704e8ed788e30fab0
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6a089d761bd3bad477e75b9e99cfbdd689d02fd528b0ec5c8a31f40022108a
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba02e5a63c4a0ddf0fa30c7fecce31d40154197f141d216232a070162ef90b7
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:52205d37ab13b9f818a1f4bb357578cf64e66697032b7434951bf1a8c4daded7
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:907f3ffe4366544061255e51e76c675abc9cc3092ca906d876edd6bdff80ab72
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5887f09cb2d9de5d6d0bc3828a2ae1a50c1eb798f38f75c10d39330ad2700401
+size 2769091588

stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d8366efe110a910a3d95b5f956d2357a7a3330dfea8db308d9bb138990da7b
+size 2769098756

stage2b-hrm-full-nocap-extra-epoch1-step330000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_330000

stage2b-hrm-full-nocap-extra-epoch1-step330000/step_330000_info.json ADDED Viewed

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

+{
+  "tag": "step_330000",
+  "global_step": 330000,
+  "stage_start_step": 317814,
+  "skip_batches_hint": 12186,
+  "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-step330000/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-step330000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2b-hrm-full-nocap-extra-epoch1 step_330000 raw resume checkpoint