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", device_map="auto")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints", dtype="auto", device_map="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

68c5e0d

verified ·

1 Parent(s): a170c31

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step770000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step770000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step770000/step_770000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step770000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step770000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -924,3 +924,12 @@ stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__4_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step770000/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-step770000/carry_step_770000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d41f483250a5935aee2356a11f64164421826248e8ea90dfb33920c89ad3b8ae
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd9fc40bb95fd4de330f3ee8c21c544c79571930e7c435ab168b1c73f5b379f
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cca4e4bf6d232f21c66579a61e511abaaa8f4eb2a7cbe07ddbcbde43a33fd37
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d42c7c5e4ff18d23f5f99557dbff04ed64effda4a358a839bfb3b4eea8eaa8e
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5e93ab9a8678c1c76ff5178470912f5e11e681ec232c5ec543e5cbaa34aa3c
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:321546c7d3b2910762afe7535c080853e7201f9245cda2b67e8d3307a2b83a73
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2134f5bc011f2dd10d3a4e1abbd4222ca7a0ed27a52b9d2d9274023b1f1f4283
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/carry_step_770000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fc717e3d416dde4cb0dfa13bdab4365a96fddebdc59985c2f38ead3dc215992e
+size 1333

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5224b689c5c2bff186c74d77a9d400f106ea9ff53323e2609b21f6eb080bbe21
+size 983812

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd41fab11c231a4dc8f44d07eff340f76d39d3125286ee75942311f86219f277
+size 2769065329

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:88832a0ada558b764d53cdaf3ca3fb774d422cf2297f6ba75bc575dcf5cf2313
+size 2769090643

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:db59b042b617efad85664f27b14bd814ba2979ac296b752dbbe4acb773502f4c
+size 2769090643

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dc370ec144eee4dabe139edd566901d757543dba00c679f6ef6a40dbd0110ff8
+size 2769090643

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc45126a5b531ad420ac0089dd2759faa7956aa86d11f0e0d0b83a5e2bacfa53
+size 2769090643

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb7a3cccd5899aa3d17fa680271d70959f2edb4321a33d03790001ba0764503
+size 2769090643

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7be63b3fb4f96cc5ff0a534379e506255aa512c6467a7e1f510ea863931b194b
+size 2769091588

stage1d-hrm-fastcap-repeat3-step770000/fsdp2_step_770000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:10841ee3e6dda804c774d005ac8b7aaf64fa063e731eb2dcd6bb4de8f45eb140
+size 2769098756

stage1d-hrm-fastcap-repeat3-step770000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_770000

stage1d-hrm-fastcap-repeat3-step770000/step_770000_info.json ADDED Viewed

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

+{
+  "tag": "step_770000",
+  "global_step": 770000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 67044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step770000/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-step770000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_770000 raw resume checkpoint