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

0c84bd6

verified ·

1 Parent(s): f27d044

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2c-hrm-full-nocap-repeat2-step590000/all_config.yaml +46 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.0.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp +3 -0
stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt +1 -0
stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json +8 -0
stage2c-hrm-full-nocap-repeat2-step590000/train_metadata.yaml +13 -0
stage2c-hrm-full-nocap-repeat2-step590000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -708,3 +708,12 @@ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp filter=
 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2c-hrm-full-nocap-repeat2-step590000/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-step590000/carry_step_590000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5725b1c387d769870ee247d66d644856de4f414c6028a43b8b831e4f416942f2
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bc44d89cd6baf153cf40a385fa3a7626c96f54c4383f0904c96e535fe2cdfe
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e2a1e577fea76e7c3cf73fe2c0db8fd0de37728a2b1a05ded2190bb5c91101
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8206d5c40f00a09247b1e8af38584c630a246352e525ea8d354b14178f3697e4
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c86553a7c52f4228de77b25e21e79723bb967c7fc972bb1c6a46e10e96377c7b
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c776002f3c55db0d1944baa3b5af451d7e841463c6806ddd1b81026cb2042164
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7e271413c5f589106bee9d649c01b32299da9396cf7fd241822a7234777442b2
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a2cde857e21576a0611366c0f11cc8fbced20ecf504ecb80d624d9c9686482
+size 1333

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0992f844ba808553761f04e30dc3352e79e54a0d1297f268ead6892d2ae5e735
+size 983815

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f2ea1a8dfd4b42594448ced0753f1b7c71aed6a7deb8c55794c5727e08a76f
+size 2769065329

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:626dca18022e89e130c34ba6b433eccc088994e58d13ff4d7748ce00de830dfc
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bddb19b49d5a6fa6982517b20f0781def9d3cce07d62d195f4fff56e012df655
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5bba7d216474b560ea98c6d821deeb77f5e1ffaadf085062dfab2167b68ca8e4
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:48562f50462dda92664c19ec01e0aff2c697c4a4be870beee41344956e2e4131
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b542f7d60015e75687969436a41367090ee3ec8e763c673c160481de2128431f
+size 2769090643

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d397b5b7925b1458cccbbbbeefb0e53d7e34adcccaa990720bad00dfa580c406
+size 2769091588

stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:54a0dabddce84b6fa33779474874694524a9f631812b2e2d44c8dad647319dbc
+size 2769098756

stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_590000

stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json ADDED Viewed

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

+{
+  "tag": "step_590000",
+  "global_step": 590000,
+  "stage_start_step": 550699,
+  "skip_batches_hint": 39301,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
+  "global_batch_size": 180224
+}

stage2c-hrm-full-nocap-repeat2-step590000/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-step590000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2c-hrm-full-nocap-repeat2 step_590000 raw resume checkpoint