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 26

Commit

2f8ab84

verified ·

1 Parent(s): f83c44c

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1b-hrm-fastcap-repeat-step260000/all_config.yaml +46 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.0.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.1.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.2.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.3.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.4.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.5.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.6.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.7.pt +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/.metadata +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__0_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__1_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__2_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__3_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__4_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__5_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__6_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__7_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step260000/latest_checkpoint.txt +1 -0
stage1b-hrm-fastcap-repeat-step260000/step_260000_info.json +8 -0
stage1b-hrm-fastcap-repeat-step260000/train_metadata.yaml +13 -0
stage1b-hrm-fastcap-repeat-step260000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -339,3 +339,12 @@ stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__6_0.distcp filter=lfs
 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step250000/fsdp2_step_250000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1b-hrm-fastcap-repeat-step260000/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-stage1b-hrm-fastcap-repeat-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-stage4-korean-tool-finance-gbs180
+resume_step: null
+resume_step_offset: 237192
+run_name: KoHRM-Text-1.4B-stage1b-hrm-fastcap-repeat
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60692600d8c462d18539716a1f1e3b8ffa8b769f54032779de62864495db73d
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e08c8feaf5998a429fc72894ee0f7112431315f8063ef1e3946d016fc9325078
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e203b188fad3fa1463764028838070656d2128f9be9556167d17fdeab63818a
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a734fc0fa02de3325d991cb1d94bf6a9b861dd96382f82a278826e13b79985
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d96a58aa47142533279343807346db9ac86f95fc48e91a77c45c0022b4b720e
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a86a370a28686e27f4ec7101aa41994b4c588d61f2bdcb31e8afb9dec27f6a4
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bf76eb1a08784a1cdb613e29313d014ee8a47a572d121c8ea3e440b76f1ac104
+size 1333

stage1b-hrm-fastcap-repeat-step260000/carry_step_260000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4d298950e5dd051cb5554bd1e4bb041e2c35d58130a3525e0dc98f5f084d24
+size 1333

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0363c57b547520ded7cbfa850c70551176837c87534485a493a3422b509b94
+size 983811

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:79ca35446dd85091365eb7b5af1f67b6d49cd86dc70c24361147f3d3934b47f7
+size 2769065329

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b732e5b8347dd1145ddce9ac9e6445690bfae5ec2a12233770fa17d74f9fad5
+size 2769090643

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4864ee2fc9a22d8b60c5bd4d04832cbc69db840ee45be789ee61821253af54e9
+size 2769090643

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8c65d8b95a1105e59b128936782068e1a5768e3d9f3685dffe36c7600802c5
+size 2769090643

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe98d1edad9d1daa668290447ba32c20f5d21e4fdf2210459944eda506554d0
+size 2769090643

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cda9049488de129c06870d065f4b46df00be243523e6da4cca00fd335737fd54
+size 2769090643

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:02da271d8f1c13aca0f135140772acc59023e5a4caaafd4cb4690c9a7ea7232e
+size 2769091588

stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5c46a8fb8673a646df92475613ce53a11608d315fa894af98e3da26e3e3ef1
+size 2769098756

stage1b-hrm-fastcap-repeat-step260000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_260000

stage1b-hrm-fastcap-repeat-step260000/step_260000_info.json ADDED Viewed

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

+{
+  "tag": "step_260000",
+  "global_step": 260000,
+  "stage_start_step": 237192,
+  "skip_batches_hint": 22808,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1b-hrm-fastcap-repeat-step260000/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

stage1b-hrm-fastcap-repeat-step260000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1b-hrm-fastcap-repeat step_260000 raw resume checkpoint