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 Jun 1

Commit

a170c31

verified ·

1 Parent(s): 98fd2bf

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step760000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step760000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step760000/step_760000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step760000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step760000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -915,3 +915,12 @@ stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__4_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__4_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-step760000/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-step760000/carry_step_760000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dc425df58642fed6f0e3368d5c803fac0e30aaddedb916872e27abdc479bc872
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:005df5b4c468981ba03d8d355798db45590b0aab69a61dffa3fadbfceff9bce9
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7057effa166542c6ed61442f176812573e0aae77e749ad40e804e4a717be59a8
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:20c674b32bfca097108f7c8637c4079d653ad44e5e25c7f177a0566740b0b1c2
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7b1661850f4e71fa066a6c9ea0e1e7875070da91fdb51f81794c39d23137da
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f492ff678ba59c704cc05733353f7369e13be2f57a445e0ebb0ad0d18a0475cc
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:54bfc2c90406277104fc71063c31ed88b0900d52798f93df6bec714a02f87e0a
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/carry_step_760000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3a7f46509d73787f23fd21e571c0639d8dc2ecdc7efcdc4d2a46741d09ed86
+size 1333

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4115c7a7b4f59b3197029f1284906f8acaa65f71345517bb824c75bd0f397dd4
+size 983812

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7df18bb1f39a870c0c7200a436601f951f718f06e41050919f00aa11493de72f
+size 2769065329

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f78a2132895b5a9b23a5f768cda9c7bee4b0951d48c8c749df29a2915631f10
+size 2769090643

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:09b07b88775760386394c6f18ee7c14d2d55f1ce8e8836faa69430771bc75f81
+size 2769090643

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f349c24f001118cd3567945f507d0652f5c95080e7150d44619d1ab4460e0c70
+size 2769090643

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6d17e8a34a0c118a1b699bd9d696ba6c7fc350e73cc235e3531c304a98e9cb1b
+size 2769090643

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:566d8a20a08ac09b763b268b1f7515a7b618d0caae62afdf102facf83929b592
+size 2769090643

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c38d67bcec5af4c36478c55905fa289be118291b3854597271329d5567a8327
+size 2769091588

stage1d-hrm-fastcap-repeat3-step760000/fsdp2_step_760000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a754ffc5d1891ee2c5c62733fe756c6a64632fe6fb038b559927d78bba6603
+size 2769098756

stage1d-hrm-fastcap-repeat3-step760000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_760000

stage1d-hrm-fastcap-repeat3-step760000/step_760000_info.json ADDED Viewed

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

+{
+  "tag": "step_760000",
+  "global_step": 760000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 57044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step760000/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-step760000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_760000 raw resume checkpoint