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

827f756

verified ·

1 Parent(s): 8152a6d

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step730000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step730000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step730000/step_730000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step730000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step730000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -888,3 +888,12 @@ stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__0_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step720000/fsdp2_step_720000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step730000/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-step730000/carry_step_730000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b79a1053b92a41d55f1eddded3c8e17a0d977d1528532247257db501f9249351
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:74180a5ac6999e3c416f54f80ca287a2578d318cf37f5cf1bb05a0eac71f9a55
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:517139731da10aa2a1bdc79d21961656069b1811c2faa5727b4882d397669ecc
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e44aacccc7f25336928a746bacd96d0649fa0f6bae19d8ecf338bf40b22c295
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8d06093105afac73b6e58837d309deecaba2bc8ae5ff071c2b171468b14d04
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1f33eb304f1f05f24a74d663d226fc1113b7898662f7b9838fef5723bfdb7a
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:08994b5ff4bbf1e2ed488b228379743d0efb1eafcc6daf88bb3ad60fc07c99e9
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/carry_step_730000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:829c92c73a0b60894672d89248c93cfb7b25b3697fb36cb7fdb09ea9897f88c7
+size 1333

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2370389ca750306dacf6956e55c886cbbe447b79a6aced33a6e9065a20a4ff1
+size 983812

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7d5d7914868848f8e6e16186fb0685761cfb3b799a02813d60b4ef8ddac326
+size 2769065329

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bff25416f0282ea05569226bbdebbce6b344c80cab48e3c5232d1e7585c469
+size 2769090643

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:874365c0e379c6af9cdcc285662faf5f16ec778d7016aa8ea43bdde489240c20
+size 2769090643

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7788364613a511557129274cd222d34f781aeac417623d1abe6387c1579c47b4
+size 2769090643

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7be000fa7fbeffa3d02abd622e3409097df726d1b190d9bb551e7b675b1ba6
+size 2769090643

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:228addbb56e5e2ab14f6d42bc3d61d0ba7298f2e3c19071c6a37040390cbbdb5
+size 2769090643

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:49be5154266a97bccbee7227bcb53e885bb44e6bbfcf579f6feec5723d470de4
+size 2769091588

stage1d-hrm-fastcap-repeat3-step730000/fsdp2_step_730000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fadf5ca665eebe870514254ce45b3d7ce1d01193d35d882ad5f56f31b0ec4e
+size 2769098756

stage1d-hrm-fastcap-repeat3-step730000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_730000

stage1d-hrm-fastcap-repeat3-step730000/step_730000_info.json ADDED Viewed

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

+{
+  "tag": "step_730000",
+  "global_step": 730000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 27044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step730000/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-step730000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_730000 raw resume checkpoint