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 30

Commit

90c3d2a

verified ·

1 Parent(s): 7db9470

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2c-hrm-full-nocap-repeat2-step620000/all_config.yaml +46 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.0.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.1.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.2.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.3.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.4.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.5.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.6.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.7.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/.metadata +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__0_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__1_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__2_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__3_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__4_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__5_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__6_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__7_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step620000/latest_checkpoint.txt +1 -0
stage2c-hrm-full-nocap-repeat2-step620000/step_620000_info.json +8 -0
stage2c-hrm-full-nocap-repeat2-step620000/train_metadata.yaml +13 -0
stage2c-hrm-full-nocap-repeat2-step620000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -735,3 +735,12 @@ stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__1_0.distcp filter=
 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step610000/fsdp2_step_610000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2c-hrm-full-nocap-repeat2-step620000/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-stage2c-hrm-full-nocap-repeat2-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-stage1c-hrm-fastcap-repeat2-gbs180
+resume_step: null
+resume_step_offset: 550699
+run_name: KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2
+seed: 0
+skip_batches: 0
+total_steps_override: 700000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9cd776415fc8677c56ecf0333b850272f9fb9e4ad4d1202d7836dc6fdba14c
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f899e2f8afec5b3917a30e7854165ce19697a1be5032680839543b2195b459
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:780e92025160de83d973fa1fbeb33692c1c17406fa0ccd880c7fdbb817cd9ec3
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9eb4adc7f48d20538519f1a3b294cbf6467bfffac0ff901e95f2a9f22f469b
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e0202c5adf24e7652fe6b98f156a4bf202582722f47fa4c3454b75656bad3e
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e12773cf533f8be823be5d52c89a44a27e6ade724dbe477766e81503708dad
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9ab4c50ca6ac8c5854b927f0d9ce2c01fee0271a5e915359ad486bec05fffc
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/carry_step_620000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2958c777662b39bc58d212f7160f8ea682fc2a131a503bac62fafcf496a1479c
+size 1333

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8eaa53a47787a20092d3d2e0daed66cd50af8532ce901e8a7bf7737f592aa817
+size 983815

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f636371e4a7a20a50758898670a1e3e95af31dc509f691917d83e20a03207d8
+size 2769065329

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:de45d51c858f2859e7c9405a8566cc05501c904e8208a33e96b7525501e3b162
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:eea966b2d8a5ca45faf97bc70ee1eb3011575a5d9efece2a47592b51fdc549ec
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7983b94c0cc65d833b6f4f44b6f8430ae2bab0fa1e8c0b82539a4456fa586a41
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8d85da08957cc4689c8982892f1a703b7e9a653be2fccffb6fff2fa203e446
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfdfb939dd0792897593dea794a625d20d68f0b8bf83a305282e94075aeb9424
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd4a8f012635430046daba0f6b1dc8253c4dd2e4d9fd9e8b3d94328b8f4bf78
+size 2769091588

stage2c-hrm-full-nocap-repeat2-step620000/fsdp2_step_620000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:234af20a90834fad4c4a355a2db13a01fdfd5cc149daff905c6bc3b3ba5d1c1b
+size 2769098756

stage2c-hrm-full-nocap-repeat2-step620000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_620000

stage2c-hrm-full-nocap-repeat2-step620000/step_620000_info.json ADDED Viewed

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

+{
+  "tag": "step_620000",
+  "global_step": 620000,
+  "stage_start_step": 550699,
+  "skip_batches_hint": 69301,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
+  "global_batch_size": 180224
+}

stage2c-hrm-full-nocap-repeat2-step620000/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

stage2c-hrm-full-nocap-repeat2-step620000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2c-hrm-full-nocap-repeat2 step_620000 raw resume checkpoint