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", 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 25

Commit

8bb2014

verified ·

1 Parent(s): f34b5a3

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3-local-terminal-step200000/all_config.yaml +46 -0
stage3-local-terminal-step200000/carry_step_200000.0.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.1.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.2.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.3.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.4.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.5.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.6.pt +3 -0
stage3-local-terminal-step200000/carry_step_200000.7.pt +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/.metadata +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__0_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__1_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__2_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__3_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__4_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__5_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__6_0.distcp +3 -0
stage3-local-terminal-step200000/fsdp2_step_200000/__7_0.distcp +3 -0
stage3-local-terminal-step200000/latest_checkpoint.txt +1 -0
stage3-local-terminal-step200000/step_200000_info.json +8 -0
stage3-local-terminal-step200000/train_metadata.yaml +13 -0
stage3-local-terminal-step200000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -249,3 +249,12 @@ stage3-local-terminal-step190000/fsdp2_step_190000/__1_0.distcp filter=lfs diff=
 stage3-local-terminal-step190000/fsdp2_step_190000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step190000/fsdp2_step_190000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step190000/fsdp2_step_190000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage3-local-terminal-step190000/fsdp2_step_190000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step190000/fsdp2_step_190000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step190000/fsdp2_step_190000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step200000/fsdp2_step_200000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3-local-terminal-step200000/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-stage3-local-terminal-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_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-stage2-hrm-full-nocap-gbs180
+resume_step: null
+resume_step_offset: 165617
+run_name: KoHRM-Text-1.4B-stage3-local-terminal
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage3-local-terminal-step200000/carry_step_200000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca81c98d89907e29bdd9dc359709d9c36aa0a3f7012e47d3064210232a18cea4
+size 1333

stage3-local-terminal-step200000/carry_step_200000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:445711fd0be963f84dba37118c37a1f6707bd586db9b8b5697b716cb42a4604b
+size 1333

stage3-local-terminal-step200000/carry_step_200000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:77197a926497e2b8964c338870e00654b6d92e2580d5e308ae950c1fc4efe775
+size 1333

stage3-local-terminal-step200000/carry_step_200000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a61d618d57911a47cd432b06b57f0fad77e02b0821e96a68b1ab335b5b6f1b
+size 1333

stage3-local-terminal-step200000/carry_step_200000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a4e9ed6aed0a7fcba5c7ca1915126bba987610ab298af389d1694c6788476b
+size 1333

stage3-local-terminal-step200000/carry_step_200000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a113afb4ce5044c362872456ed5d3ae8518f7265205976cab93fc4fe56e1da41
+size 1333

stage3-local-terminal-step200000/carry_step_200000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a6db6524e8f6c3dbe013f665651709c4272e8c0bf7f5ce7b55bd1f08c1c2be38
+size 1333

stage3-local-terminal-step200000/carry_step_200000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9896d306db3c6160a20521f61d1276a56dd5be470a0e5206b709e7f64681e07c
+size 1333

stage3-local-terminal-step200000/fsdp2_step_200000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f619d2ba06d0b0aa675fe872b04fd3e3a35f610e75f6a8b5d329ba4bdb2ce427
+size 983806

stage3-local-terminal-step200000/fsdp2_step_200000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:83325535fdc926d7a3a4eef78bc62af160a3ea82b9501c3dd02ce8c8e5a73a4b
+size 2769065329

stage3-local-terminal-step200000/fsdp2_step_200000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5535cbbc46df13f2d84a38ef2bbb773831a7512d615169f17e1f68df402fbf7
+size 2769090643

stage3-local-terminal-step200000/fsdp2_step_200000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5a16b41c04ff9819a03df546479b85cd1d3f22071c772d68cf428f15aeb4c2
+size 2769090643

stage3-local-terminal-step200000/fsdp2_step_200000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf25b1ec98882d93073865ed34ae4750814175310fddeb8ad591a04a92f1692
+size 2769090643

stage3-local-terminal-step200000/fsdp2_step_200000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d8dcf60c5f90bf742b164f62c6c932e7340e7c30fd37ac31c2f369a179dfd1a7
+size 2769090643

stage3-local-terminal-step200000/fsdp2_step_200000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:81e9293b1d3bb980e7b7edeb7a13eb9eb70106be92b4c085aa597198aeb3cd28
+size 2769090643

stage3-local-terminal-step200000/fsdp2_step_200000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a1c9ec2a72287779f9f05b2033f7275e219c8c61f731e05a6880d720e8b3f2
+size 2769091588

stage3-local-terminal-step200000/fsdp2_step_200000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba4dc4da38125cfd654ae5105804c27877af54e28db37c2bc0fa478cf5f04b0
+size 2769098756

stage3-local-terminal-step200000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_200000

stage3-local-terminal-step200000/step_200000_info.json ADDED Viewed

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

+{
+  "tag": "step_200000",
+  "global_step": 200000,
+  "stage_start_step": 165617,
+  "skip_batches_hint": 34383,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3-local-terminal-step200000/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/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1
+total_length: 9386532467
+vocab_size: 131072

stage3-local-terminal-step200000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3-local-terminal step_200000 raw resume checkpoint