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 27

Commit

6480e48

verified ·

1 Parent(s): dbef626

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/all_config.yaml +46 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.0.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.1.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.2.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.3.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.4.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.5.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.6.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.7.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/.metadata +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__0_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__1_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__2_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__3_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__4_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__5_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__6_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__7_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/latest_checkpoint.txt +1 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/step_340000_info.json +8 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/train_metadata.yaml +13 -0
stage2b-hrm-full-nocap-extra-epoch1-step340000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -429,3 +429,12 @@ stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__3_0.distcp fi
 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step330000/fsdp2_step_330000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

stage2b-hrm-full-nocap-extra-epoch1-step340000/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-stage2b-hrm-full-nocap-extra-epoch1-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_extra_epochs_1_3_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-stage1b-hrm-fastcap-repeat-gbs180
+resume_step: null
+resume_step_offset: 317814
+run_name: KoHRM-Text-1.4B-stage2b-hrm-full-nocap-extra-epoch1
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6205189704b260873f4c24ec2650b6ffcf59f6dfa9bc314d25d667adcb0a9fc2
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8cde33c8ab2930f8530b6f7fec7770bd9402a6cbada399b80d518bf55ceed1
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6892f25d2f970538ea521a46ba3e1af26a3f7836052531e35f2178edf3fd3583
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:097fb8adf648ddbacb5efe2332487296ee5cab908cb8860dfb0f48451d492bed
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff2666442986d3924ac4ac82bcce6b358c2ee32e6c979fca3e0e16fcc7a83f8
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf04d5bc79a983d113b19b83a9e58a29997b59127e52fdb13c99b566a731722
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8ddc9c68d47c64277532ac4140e49b9ad8e73e6e138657ab3d51c9b9f83f85a8
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/carry_step_340000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d9703f640c7a5484199cee0b3c0a424092e5ba6b92dd574b71d7e1cbbf0c0dab
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:504b45b8ccc00ae9c7fb125f1d6d003cba0a3e3612c70ee3920e938af8aa0267
+size 983820

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cab7f37f8a8295e915d11588376f360bd73ef8cf1a1c53e57a6259361b631bf
+size 2769065329

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:124c67617c7603ab5c53a637ddf95437186a6f17fb04d8bbca659cf33aa54cf0
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a482750e67be6e915303627e42b71bce794c7c18342f89183ece0d4a3e63cbff
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b78d42d0900da08edceb2f8ef170d1aed31b7b753a3ded6ccfddf6dfcbd6f94
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a590df1fa6c4a658dfc36c43a90157a7a99a4cf313c3b6e833a06ac48e056345
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:74f1b52cf6a9863737c8c44623640e8379ed1ecdc4f6cb5ef6cbb9ed357665fa
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9d9d68caffabe8206e4c27e9c768ecc3d1fc9ca3406d6155bbd0e4b64120ba
+size 2769091588

stage2b-hrm-full-nocap-extra-epoch1-step340000/fsdp2_step_340000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7325f731b9a082b3fbb207bfd3c2b9ce7b28d4018d0aab8432e44504c26f741f
+size 2769098756

stage2b-hrm-full-nocap-extra-epoch1-step340000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_340000

stage2b-hrm-full-nocap-extra-epoch1-step340000/step_340000_info.json ADDED Viewed

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

+{
+  "tag": "step_340000",
+  "global_step": 340000,
+  "stage_start_step": 317814,
+  "skip_batches_hint": 22186,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_extra_epochs_1_3_v1",
+  "global_batch_size": 180224
+}

stage2b-hrm-full-nocap-extra-epoch1-step340000/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: 14553638506
+vocab_size: 131072

stage2b-hrm-full-nocap-extra-epoch1-step340000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2b-hrm-full-nocap-extra-epoch1 step_340000 raw resume checkpoint