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 8 days ago

Commit

98fd2bf

verified ·

1 Parent(s): a13cf72

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage1d-hrm-fastcap-repeat3-step750000/all_config.yaml +46 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.0.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.1.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.2.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.3.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.4.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.5.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.6.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.7.pt +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/.metadata +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__0_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__1_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__2_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__3_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__4_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__5_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__6_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__7_0.distcp +3 -0
stage1d-hrm-fastcap-repeat3-step750000/latest_checkpoint.txt +1 -0
stage1d-hrm-fastcap-repeat3-step750000/step_750000_info.json +8 -0
stage1d-hrm-fastcap-repeat3-step750000/train_metadata.yaml +13 -0
stage1d-hrm-fastcap-repeat3-step750000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -906,3 +906,12 @@ stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__6_0.distcp filter=lfs
 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/.metadata filter=lfs diff=lfs merge=lfs -text

 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage1d-hrm-fastcap-repeat3-step740000/fsdp2_step_740000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text

stage1d-hrm-fastcap-repeat3-step750000/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-step750000/carry_step_750000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b247efd27c5d7e9b011044aa8b173ea5b936afbe33eed2086a1b5cdc855bdca9
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb13dd000f56320fa80aa39cd1f019b994d95c55572bfa9ba54376197d237be
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:64e5070bfe759199f05a9a1515e7f050c0a64b2c39ddd224f5044064f14d445c
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7c5a9a7b7e9d6a9437206335761736fb77c33f629582419545410082fa6ae0
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce4a7411df02960a1db8e9b4ce54abe70d5694c2b5eaca22eadde7f0696a376
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5a460ef346ff4d58c362d21cbe0d2351a3b73f8737068356841b7566ce9301
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a117e0a53f2bd2fa957c69de8aebd4f7867eb840f65c26af5d4e4ea0b20f5b6
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/carry_step_750000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9a258dd4a0adeeeec293147c306aee9d77586f87908fad7c9540dafcb8e1a9bc
+size 1333

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7954f0b94cc99906d1a01f8bf38a300f38725c4aaa99e21601441cc36bf528de
+size 983812

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:26fb11ca08197ac75da1833d010f625589743f68315f2be818a340fc0722f043
+size 2769065329

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef84a446c9d28ac52f9b3445192b6e196fac417abb3adfa7b7baf9e69f3bfb5b
+size 2769090643

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:456d21edb5761ec854ffb84c976bacbf492318f2d70f7faf78a18c0f1a3cf246
+size 2769090643

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6bf713d5be85ec182037db503a9eb32c0bb619a1479ef0c41e8054e7dd2e6f
+size 2769090643

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:690a8f7415951fe7f35d007a8ae6b4440da35c77e06b74c0e66bf7085bfbcab3
+size 2769090643

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d336f36e2531125377d3575f9959b66c3535861f51fd9e8cb2045e4d5fbcbc
+size 2769090643

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7a9b27301048d6b29da8c577e0699ef754f787cfa68aaeee5cb47cd0d51a3c
+size 2769091588

stage1d-hrm-fastcap-repeat3-step750000/fsdp2_step_750000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bb1fa8ad7669b81926be94abba7dff94e605d87ab0e24843c8b52be7d85235
+size 2769098756

stage1d-hrm-fastcap-repeat3-step750000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_750000

stage1d-hrm-fastcap-repeat3-step750000/step_750000_info.json ADDED Viewed

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

+{
+  "tag": "step_750000",
+  "global_step": 750000,
+  "stage_start_step": 702956,
+  "skip_batches_hint": 47044,
+  "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
+  "global_batch_size": 180224
+}

stage1d-hrm-fastcap-repeat3-step750000/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-step750000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage1d-hrm-fastcap-repeat3 step_750000 raw resume checkpoint