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 29

Commit

5daa669

verified ·

1 Parent(s): 627cc6b

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1c-hrm-fastcap-repeat2-step540000/all_config.yaml +46 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.0.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.1.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.2.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.3.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.4.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.5.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.6.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.7.pt +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/.metadata +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__0_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__1_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__2_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__3_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__4_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__5_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__6_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__7_0.distcp +3 -0
stage1c-hrm-fastcap-repeat2-step540000/latest_checkpoint.txt +1 -0
stage1c-hrm-fastcap-repeat2-step540000/step_540000_info.json +8 -0
stage1c-hrm-fastcap-repeat2-step540000/train_metadata.yaml +13 -0
stage1c-hrm-fastcap-repeat2-step540000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -645,3 +645,12 @@ stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__0_0.distcp filter=lfs
 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1c-hrm-fastcap-repeat2-step530000/fsdp2_step_530000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1c-hrm-fastcap-repeat2-step540000/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-stage1c-hrm-fastcap-repeat2-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-stage4b-korean-tool-finance-repeat-gbs180
+resume_step: null
+resume_step_offset: 470077
+run_name: KoHRM-Text-1.4B-stage1c-hrm-fastcap-repeat2
+seed: 0
+skip_batches: 0
+total_steps_override: 700000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:404caddde0cf78f21ed622366dbd75e2c473b44e385d56cd61b99b7546b9f1cd
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e979eecdab5e3a9bdf6035e7fcac6382b6ea8587012f0946474e268b1e1715
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ad72ab8f9234995ceef0136fd5ad0a24ec5aa32eecee8d4c5080ba3e8f35df
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5449993f785adc52ec774839a70b0d7488788f2d61a11939e954ef9358c59599
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6d160642f3ee5c95c39672231c74a7bde9c47ec5322cb32abdb6e983cc6d96b5
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d55b9a55ca8bb86ef5a5c3b2c11805a5b53a072b3c7ce5a53efb756f6f3877c
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:715640b738ab2a40904547a088ba7304856d480e520f3f2b107ea4ec45b0afc9
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/carry_step_540000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc82485f0f955b084d4600b395fe43969124cd273da9043fa27a5bd61dd4aa9
+size 1333

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffe0ed6cbc7b34e79129364275053d28bdd786dcb8002db3282b3ca69712f7a
+size 983812

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ac5005709a43147b34d9c773d388058ca12b2066c721c35e167b05fa800f6f
+size 2769065329

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec39c992761a751b3c22b3989ef1a84b94d7f72aef804be6fc623a0ef935036
+size 2769090643

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:46e3d1e5d8ef8756d1c195765e30cd92a63a668de4aff7f03d101533fdfb07eb
+size 2769090643

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b43f5883e0533b5179422c5a25954687f829b6485d4d640f4676d4cb28bbc07
+size 2769090643

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:01b2e815e58dbe4644b7e835804aba31955e092c5c05118abbbc56ce36b5bf81
+size 2769090643

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3715b3174f50caeb018bf5aff1d3628e1c31ec3813b0d013356cada1c858c646
+size 2769090643

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd858fe94c8ad932edf2d1d6fdcaeac9914c1941e7e3923a3b8f99f1fef5ea7
+size 2769091588

stage1c-hrm-fastcap-repeat2-step540000/fsdp2_step_540000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:00f5d66b59271970ca119d9c37bfba28ef8beff4e5894ce25c813412b18be673
+size 2769098756

stage1c-hrm-fastcap-repeat2-step540000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_540000

stage1c-hrm-fastcap-repeat2-step540000/step_540000_info.json ADDED Viewed

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

+{
+  "tag": "step_540000",
+  "global_step": 540000,
+  "stage_start_step": 470077,
+  "skip_batches_hint": 69923,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1c-hrm-fastcap-repeat2-step540000/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

stage1c-hrm-fastcap-repeat2-step540000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1c-hrm-fastcap-repeat2 step_540000 raw resume checkpoint