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

a13cf72

verified ·

1 Parent(s): 827f756

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step740000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step740000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step740000/step_740000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step740000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step740000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -897,3 +897,12 @@ stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__0_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/.metadata filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step740000/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-step740000/carry_step_740000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:492f243cbfe082b63c47c52508c593f04be5ffad796d0e82425405c20e00728b
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b0e0d22bf885c99f0bb968a5c7e536f6835c5f5517c7ed6ad67dcfec83c5d9
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:52a38efa18a2c94c6b7586c54c4bd5fc33a05666a6563ee011eae4833496dcfb
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:83018b53ea9bb80526d444a88ec71ed8e4097334083cd78993af10f2c7431554
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:95a1f6976492f0f8755b5d4da84b18e18cc6cd9ce30ed7ea17ceb29349ce3319
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7fda54c81ddc0c158485106e8d1aeb7443bf59adb4cc258ae337f790a622313e
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0de3a416e347ae662ec9b6b94fb4b6e3bf875289836f18a4a0b4bdf2b176ed63
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/carry_step_740000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6154995c580b76f04db97345cbfccc0133cf71ee9b3a7ab0166ac50077d27ad1
+size 1333

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:de0372947e5ca6577259cf364278176a3dbcbf7dada7c9d30ab3f5d99424ff70
+size 983812

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:33e3e344d840b530f9c7128ff9b1c786e01ae650ac0b3021d24a428ef0fdf7a7
+size 2769065329

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:408381d2de57fbfa0cd98e509ba0b536b5179d4ff1906adc8703a9f819b8619b
+size 2769090643

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1880db3d975bb982525abb532efe12a825fd99a7dc73fcba88d5d75b9d8dd1
+size 2769090643

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b04cc73b7a3e13df863d2f603ca8c7c37bf9a4b88a9803021e0ba195b6d6565
+size 2769090643

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:43fb84419ae07a2afe92634ad049d180656a1bd775b2bdd4747206ac570be107
+size 2769090643

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:73156a1449d277d54b16e848add4fb8a69a8bb91637d5f01d40a142e0b2bca3b
+size 2769090643

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:848d5f3fe1de40d8045f43671d015d6f4c18210b49fa9aa00e148523acda67e2
+size 2769091588

stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:77859fc51b6f37b82a18aa0332fd0cd09b4774160ea3bcc08b77bd80c68c2dbc
+size 2769098756

stage1d-hrm-fastcap-repeat3-step740000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_740000

stage1d-hrm-fastcap-repeat3-step740000/step_740000_info.json ADDED Viewed

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

+{
+  "tag": "step_740000",
+  "global_step": 740000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 37044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step740000/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-step740000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_740000 raw resume checkpoint