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 26

Commit

b729fde

verified ·

1 Parent(s): 2f8ab84

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1b-hrm-fastcap-repeat-step270000/all_config.yaml +46 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.0.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.1.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.2.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.3.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.4.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.5.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.6.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.7.pt +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/.metadata +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__0_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__1_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__2_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__3_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__4_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__5_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__6_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__7_0.distcp +3 -0
stage1b-hrm-fastcap-repeat-step270000/latest_checkpoint.txt +1 -0
stage1b-hrm-fastcap-repeat-step270000/step_270000_info.json +8 -0
stage1b-hrm-fastcap-repeat-step270000/train_metadata.yaml +13 -0
stage1b-hrm-fastcap-repeat-step270000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -348,3 +348,12 @@ stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__4_0.distcp filter=lfs
 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1b-hrm-fastcap-repeat-step260000/fsdp2_step_260000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1b-hrm-fastcap-repeat-step270000/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-stage1b-hrm-fastcap-repeat-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-stage4-korean-tool-finance-gbs180
+resume_step: null
+resume_step_offset: 237192
+run_name: KoHRM-Text-1.4B-stage1b-hrm-fastcap-repeat
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:63ca751db4e500dab43ec7fddda8ec1e80c61d6eb2d6813757a31495e57ef4bc
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:66d003470b7c51023142eb38ca4d700d224f7deb6e530e979fc5f6b176d04c04
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2d24fdb64f792a332706e0fbfe7c26caa8a47622957eed87cf4845ebd7988c
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:131b09b7ea94264067175dd421352a5c57e2e35cdd0450554b0ff02e7986cdfb
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce13a5c7076cee7d84f989308885813f885126a9aa76940df9a5e67ab6c971e3
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c911f908301440b91d6afdf42d607224fb085a4bf09bfd31e94d94b09947da32
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d87dc790e22cf783cc876f66ef432fc26bc01898ad9d3dd8489947d30d24102a
+size 1333

stage1b-hrm-fastcap-repeat-step270000/carry_step_270000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f41953f75bc78f8bcf2ea8fe18285cd33e1f70191336a1eeb912a736d6a062e4
+size 1333

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:515e1d542710204e5ae09596f944d54fe03900c9f1fab549bfef5b593c2e5b0c
+size 983811

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5ff326ba686b961f2ae301841d48cfee1f470865b9d102eb5a21009ca916bf
+size 2769065329

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ad3ef42fd5a0a409fa24c341c22dc0cffc504a95ae1a61e8af5b7fac9f669a
+size 2769090643

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5e7b61e4ee9fd43a7968f646e660644ebd12a38fa651b80d96b9f28c6263a4
+size 2769090643

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa412141308fad69f9e8df43999771649ef386902d9ed63e223ea7acf4bb3831
+size 2769090643

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3831066994d8e719588d216158241a1d1bcb1b17708015a187c731200b3b5429
+size 2769090643

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4dffdd02460b1e9e48ad8abda42652a309964a971e265c0e6b970ac320aeef
+size 2769090643

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b10890b8301be0a1becd17fb4c8738b694466ec71625cbb26c225ce147cd0166
+size 2769091588

stage1b-hrm-fastcap-repeat-step270000/fsdp2_step_270000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4b28595667a16f2e475976d30782cc1771fe51e015161998ee91023c2117f8
+size 2769098756

stage1b-hrm-fastcap-repeat-step270000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_270000

stage1b-hrm-fastcap-repeat-step270000/step_270000_info.json ADDED Viewed

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

+{
+  "tag": "step_270000",
+  "global_step": 270000,
+  "stage_start_step": 237192,
+  "skip_batches_hint": 32808,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1b-hrm-fastcap-repeat-step270000/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

stage1b-hrm-fastcap-repeat-step270000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1b-hrm-fastcap-repeat step_270000 raw resume checkpoint