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

456c662

verified ·

1 Parent(s): e4f5238

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1b-hrm-fastcap-repeat-step310000/all_config.yaml +46 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.0.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.1.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.2.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.3.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.4.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.5.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.6.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.7.pt +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/.metadata +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__0_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__1_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__2_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__3_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__4_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__5_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__6_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__7_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step310000/latest_checkpoint.txt +1 -0
stage1b-hrm-fastcap-repeat-step310000/step_310000_info.json +8 -0
stage1b-hrm-fastcap-repeat-step310000/train_metadata.yaml +13 -0
stage1b-hrm-fastcap-repeat-step310000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -384,3 +384,12 @@ stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__6_0.distcp filter=lfs
 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step300000/fsdp2_step_300000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1b-hrm-fastcap-repeat-step310000/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-step310000/carry_step_310000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d6f28ef3c85f170b821a8767935e58dee86a2861d5ccf97421a7ff530eb4b
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:961afdf1cfe288c54600418f32c68b17341d65472b99342bdadc9505ebe73f5c
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1b1677e0e606f834986ce943044ae4a7c157ba9b721046a078f16e4a31819c
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:04e9e45713d5396e7b8c4df99a38cf9ee0290c9d93b2a1c019e2ae771861ad5f
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:484b0bb1fcf296ecfd97a36aadeaf0746bdd34aa1f7c38776d0ca0becbc8594e
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:51a245d840aa3f7386d63d6051ffd28408590768700733b22b820245a99b2ed0
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e61153399ebbdef42ea372998b32bb44bd6954ef9afbcb98c0d5ce805ad836ef
+size 1333

stage1b-hrm-fastcap-repeat-step310000/carry_step_310000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bfeb840a1a8e588689c4d2b23f8e26ff99090b842561849c046b0ed6ebebe58d
+size 1333

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbbe207316b429606282cd0e35fbe10ee0f1854b8b919723ce269b3345ff238
+size 983811

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:41d0384aca1d1d1caf7a6658c040186a240ae300cb357c646510879fb6c5592a
+size 2769065329

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:354292e75c135070dd9f17c867da8d343e5b15b87ae8750b89eda6ac7adfb994
+size 2769090643

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:18c51635eb8a273f44df62eef622a1d830e5f2e5f805144ebee6336995acf5fd
+size 2769090643

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca83306d419a74817d148e04ce0cde017369af7839880eabf3cc30474ecf2a13
+size 2769090643

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:54d30a28b480ebc594ba75a4cb0c3e99e5b298807ef0b6db097a40e489d0c5d5
+size 2769090643

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:af9f32b32e0d5994796774a324aef243c83e57d866bf00e2212ef3153dfd9769
+size 2769090643

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d919fe36972816fcafd57d0cdde1a3c8de4d98577c17a893b4ea205cc99a6b78
+size 2769091588

stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ac024a9fee171e2a82f369e32236ecf1acef89838b3f29ca4f4b8401470c74aa
+size 2769098756

stage1b-hrm-fastcap-repeat-step310000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_310000

stage1b-hrm-fastcap-repeat-step310000/step_310000_info.json ADDED Viewed

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

+{
+  "tag": "step_310000",
+  "global_step": 310000,
+  "stage_start_step": 237192,
+  "skip_batches_hint": 72808,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1b-hrm-fastcap-repeat-step310000/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-step310000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1b-hrm-fastcap-repeat step_310000 raw resume checkpoint