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

ba308fc

verified ·

1 Parent(s): e902b17

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2d-hrm-full-nocap-repeat3-step790000/all_config.yaml +46 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.0.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.1.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.2.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.3.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.4.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.5.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.6.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.7.pt +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/.metadata +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__0_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__1_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__2_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__3_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__4_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__5_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__6_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__7_0.distcp +3 -0
stage2d-hrm-full-nocap-repeat3-step790000/latest_checkpoint.txt +1 -0
stage2d-hrm-full-nocap-repeat3-step790000/step_790000_info.json +8 -0
stage2d-hrm-full-nocap-repeat3-step790000/train_metadata.yaml +13 -0
stage2d-hrm-full-nocap-repeat3-step790000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -960,3 +960,12 @@ stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__6_0.distcp filter=lfs diff=lfs merge
 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3/fsdp2_epoch_1/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2d-hrm-full-nocap-repeat3-step790000/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-stage2d-hrm-full-nocap-repeat3-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-stage1d-hrm-fastcap-repeat3-gbs180
+resume_step: null
+resume_step_offset: 783578
+run_name: KoHRM-Text-1.4B-stage2d-hrm-full-nocap-repeat3
+seed: 0
+skip_batches: 0
+total_steps_override: 934306
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0224337d442695ef1c4276adb9b6901cb700f4c2f4caa01515771fd5db1bd627
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f804e240a0baf122acb7080f56402285f7775bc596c81a5451a01136126a253
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b9744f8071cd82edf845982f6585b6bf276129040ec422060911ff99ce7c11
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6829b37b6dedca832be619bb23ca5301b715a24db2810ff809ac3b42d3aa3949
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:831a2f1aaa141aff8f2af05e88069a17a84cf67223ea8e72c9c9f86746b3f019
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8804507d2db6fcf76eeba5a9b795563f5f1c208083aab2528e44294dfbf8cff9
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:df65a4469ff33aadd00ed6011aec892391bb0bcff51e17b47e9fa4251e3d7f39
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/carry_step_790000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:38073d23ebe195c7daf34f0c4ba4c0318c83199d6cfeb4a0d5b78da14771510a
+size 1333

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:08f7182809f737d6a242d14a2215a03562d92cffa2f443381d36c3c670233cb4
+size 983815

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5127bc046ae0591db77e0c6a163dcb13375b2648c2c830651ae4bfa7bf3b50b8
+size 2769065329

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c64a210b8a9697f449747f507b15544aaa4f9503e1cfbccc997cb1c22113f7c1
+size 2769090643

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbbee7048ef0ccc47da8bd2efd000afb7f45a4b1787a0cc9ad41283d5ce7256
+size 2769090643

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed93886736cb0aea669ea13a15c61244da460c83aa38c7e8996e8d95c541a96e
+size 2769090643

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d75a5597848930b1d3d0a4982b8561dd23d479dcb5aff0153f92a96f62c5af2d
+size 2769090643

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e67d9b33a7778f305aad49f9017a69ea440bfc30f763b824554e0242b919aed
+size 2769090643

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60a52acc8fad5f7eae8504417e3853a89bde29d847483cedcd4ffeb6d0b8c91
+size 2769091588

stage2d-hrm-full-nocap-repeat3-step790000/fsdp2_step_790000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7680351d7e669b2d528ad0fee55c8d33a0459bacb790cd1ec04ebb79fc5ce4a2
+size 2769098756

stage2d-hrm-full-nocap-repeat3-step790000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_790000

stage2d-hrm-full-nocap-repeat3-step790000/step_790000_info.json ADDED Viewed

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

+{
+  "tag": "step_790000",
+  "global_step": 790000,
+  "stage_start_step": 783578,
+  "skip_batches_hint": 6422,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
+  "global_batch_size": 180224
+}

stage2d-hrm-full-nocap-repeat3-step790000/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

stage2d-hrm-full-nocap-repeat3-step790000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2d-hrm-full-nocap-repeat3 step_790000 raw resume checkpoint