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 May 28

Commit

8fa783b

verified ·

1 Parent(s): 626dfd3

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/all_config.yaml +46 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.0.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.1.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.2.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.3.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.4.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.5.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.6.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.7.pt +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/.metadata +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__0_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__1_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__2_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__3_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__4_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__5_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__6_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__7_0.distcp +3 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/latest_checkpoint.txt +1 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/step_390000_info.json +8 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/train_metadata.yaml +13 -0
stage2b-hrm-full-nocap-extra-epoch1-step390000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -474,3 +474,12 @@ stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__2_0.distcp fi
 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2b-hrm-full-nocap-extra-epoch1-step380000/fsdp2_step_380000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/.metadata filter=lfs diff=lfs merge=lfs -text

stage2b-hrm-full-nocap-extra-epoch1-step390000/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-step390000/carry_step_390000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a596c26fedeccfb0895fbb9a03d6cfb1485a83ef6a4406bce964b721fa447f6c
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4601849836d64efe8d709d62d67482a7d1a38d1df81978e3c55bc4ace1e0d3
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7279744cf5f6ff37556986a8fa802c74d868d73079f67a5393a47efaea8c69d3
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f98090c6fe1f0e75435daabb9198162e027459d6c2fb50339054f8d49abe9ec2
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b17632f4febb2fc864fbf4e90401f250ce20741e26996f055108a6929c71b0
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c63df707365ca4501693cbfe32e585d3d5d83e09f6fbe6b228c9b5b83012d9
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f88bfbbd98fd127b612eba6da694d6db4717152854ffe2380d6e2ccc9a6f633
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/carry_step_390000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:78f3032699fb4f88d2e880abb9b3c3b1f4c0b5dc570d58f1419610fa6e8d0795
+size 1333

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bdba79cbb151b5ae5b029e36650980d9976a55cb3b0664a8868f4405c698c6a
+size 983820

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b3755ceeff73cf5b1ead4c9f7dcd162115b4653fa4da42524a39dce2f88588
+size 2769065329

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1971d18d9f61ea6a5a4b704c16d00b2bd85429a1a5f4b72246e8eae646fdf4db
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a711cc58d012a5ce610144b35f856a71ab0ac3f1d3ef648a9d6a532cbaa7a290
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e03451a38647185d28c9d62f48c7fdc87d32944fb8660bec76eff591194931d
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:248709352c6de4b0ea0f0f1ddb4eaf6d5fcded2eb4af73f1c0dc4f61d6c4b151
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd312134586d38dd8405cecde80f3d7f4e7b44ff23ffb72431d07ab393497480
+size 2769090643

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f75102bc9228fc052df02352f0b323104e8505ef205c08534513d4a783b178a2
+size 2769091588

stage2b-hrm-full-nocap-extra-epoch1-step390000/fsdp2_step_390000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:80f6f8a42d3b17da6e8f4063347a5c0f4fb16d876c70ef897c893f08dfc7dd72
+size 2769098756

stage2b-hrm-full-nocap-extra-epoch1-step390000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_390000

stage2b-hrm-full-nocap-extra-epoch1-step390000/step_390000_info.json ADDED Viewed

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

+{
+  "tag": "step_390000",
+  "global_step": 390000,
+  "stage_start_step": 317814,
+  "skip_batches_hint": 72186,
+  "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-step390000/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-step390000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage2b-hrm-full-nocap-extra-epoch1 step_390000 raw resume checkpoint