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

4d33679

verified ·

1 Parent(s): 6480e48

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/all_config.yaml +46 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.0.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.1.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.2.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.3.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.4.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.5.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.6.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.7.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/.metadata +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__0_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__1_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__2_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__3_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__4_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__5_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__6_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__7_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/latest_checkpoint.txt +1 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/step_350000_info.json +8 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/train_metadata.yaml +13 -0
stage2b-hrm-full-nocap-extra-epoch1-step350000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -438,3 +438,12 @@ stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__5_0.distcp fi
 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__3_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-step350000/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-step350000/carry_step_350000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7299bc96e73980dd4a0640f3d60582e6a025c99d3a5fce58c000bde11db71674
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5df4f59854bd81b2f0fc070e1edbfbbeeb982bfdb481f5741895de443b1ecf
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:df48d21428d85ead3bea3c5620bfd6b194d5c51b6d1e5e45062776c333ac38ff
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3898e9f1c8883c913244d9ca230b1c516a468f66c02040562e0c88c9a9ba80e5
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a682c70123ac24dbee9067857da700cd30226518a7bc63b530d1aca76c8a9013
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:697dba7246e640fc8fc77274cc3e9a12a408c4f4b04a9efe5fadb746016e5112
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4abfddc2b5dcba51602dcd3927451bd62a06bea99decc4c573d127ff62735c1
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/carry_step_350000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2c6796a82591ae6621a4c870ef6981a076865196f0fe099c4151c97578dfed
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a69f8b9a973145921d18913023e3ed7c8d7f169eac61dbb4e6351aeb89f50b3e
+size 983820

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cea5a7278a5101f04d093df05d6504e96b76f6b4a3087b7e9f733e72fbff456a
+size 2769065329

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7e87ca0f0a20dddb9823f78a9de8f905f126a75cb5bab3bc9232473d74876e6f
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ece4e62d49599fca89d1370806b8ead450b58d75de68b1bc1aecc1ad4a18c2
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:20176e96bffc984c71189b0603aaba4b854a7d26a8fe51459492966acf7b38a5
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d5bd360daab8f2d21d13aef37d16efc986d090d324a85e4a1371375b898cfa
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:39ac4f3052fbc6142ba00ce497882982d3edff7b2914ad7da933cbad7b6f3691
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b24f37048f61feac88eb6288febd6eaf6d19294ea75349b2126b91d22b48437c
+size 2769091588

stage2b-hrm-full-nocap-extra-epoch1-step350000/fsdp2_step_350000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a025454944fbc460bece2cb85822d809a9b316516f9d5ddaab50e95b6dacb22a
+size 2769098756

stage2b-hrm-full-nocap-extra-epoch1-step350000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_350000

stage2b-hrm-full-nocap-extra-epoch1-step350000/step_350000_info.json ADDED Viewed

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

+{
+  "tag": "step_350000",
+  "global_step": 350000,
+  "stage_start_step": 317814,
+  "skip_batches_hint": 32186,
+  "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-step350000/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-step350000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2b-hrm-full-nocap-extra-epoch1 step_350000 raw resume checkpoint