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 26

Commit

93f0c26

verified ·

1 Parent(s): 0a9e4e7

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3-local-terminal-step220000/all_config.yaml +46 -0
stage3-local-terminal-step220000/carry_step_220000.0.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.1.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.2.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.3.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.4.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.5.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.6.pt +3 -0
stage3-local-terminal-step220000/carry_step_220000.7.pt +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/.metadata +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__0_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__1_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__2_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__3_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__4_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__5_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__6_0.distcp +3 -0
stage3-local-terminal-step220000/fsdp2_step_220000/__7_0.distcp +3 -0
stage3-local-terminal-step220000/latest_checkpoint.txt +1 -0
stage3-local-terminal-step220000/step_220000_info.json +8 -0
stage3-local-terminal-step220000/train_metadata.yaml +13 -0
stage3-local-terminal-step220000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -267,3 +267,12 @@ stage3-local-terminal-step210000/fsdp2_step_210000/__0_0.distcp filter=lfs diff=
 stage3-local-terminal-step210000/fsdp2_step_210000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step210000/fsdp2_step_210000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step210000/fsdp2_step_210000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage3-local-terminal-step210000/fsdp2_step_210000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step210000/fsdp2_step_210000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3-local-terminal-step210000/fsdp2_step_210000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step220000/fsdp2_step_220000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3-local-terminal-step220000/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-step220000/carry_step_220000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c584742e3318e13cbc5787b68b6d5280e691bf92703c80f008a865c4cbbea0a
+size 1333

stage3-local-terminal-step220000/carry_step_220000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:738cbe85ccc590cf35b103894b7fb73e3bed47f7629bfc755cfa7bc6b82dfb99
+size 1333

stage3-local-terminal-step220000/carry_step_220000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9b0a6f5658ad93f360a332f4aded521d342831ef31627cc82a4494926fee5a
+size 1333

stage3-local-terminal-step220000/carry_step_220000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6909700f14ba31fcf1e46737809c5ea52c0ca7b1ffd7c3d01d6fe601b1a81d9d
+size 1333

stage3-local-terminal-step220000/carry_step_220000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec02da51dd73ea593642f6acb1b01db261c00f1e5e1a9c96ec030be180226bd2
+size 1333

stage3-local-terminal-step220000/carry_step_220000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:46eba369ad9c818ddfa0b4c0f6b7e23f51b1f644f767132f5b2eb470e3e5cadb
+size 1333

stage3-local-terminal-step220000/carry_step_220000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:02cbcb5512c4905925ce8830411cf926d971b46621d6b6edfb048ba15b5e78eb
+size 1333

stage3-local-terminal-step220000/carry_step_220000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2553d0204cc137ce1e2fc56bd2c7a4d7f70ab6f9235b85515a049e2f30be53f4
+size 1333

stage3-local-terminal-step220000/fsdp2_step_220000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:64008e4d655e2ca244046bdc33ee5e7b93e492b767c7aec9b102a70d2a7737d3
+size 983806

stage3-local-terminal-step220000/fsdp2_step_220000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:846a779f06e90c6d26fcaf3379a5b535a5d0cd0c645ae997ded333aeb00536e0
+size 2769065329

stage3-local-terminal-step220000/fsdp2_step_220000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8837e9dae17e071610e2d81323f1b68f77c6c5693efcd51c33e3586603f482c4
+size 2769090643

stage3-local-terminal-step220000/fsdp2_step_220000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:39440651b3ce78dff5fe04b1fb6cbb3903e7cfb3e2a6f8e3209c32c84c228bb8
+size 2769090643

stage3-local-terminal-step220000/fsdp2_step_220000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:28b69e1eef93139e8f1201e5a3fb38864abd538092e9525edbe83b8f83b69611
+size 2769090643

stage3-local-terminal-step220000/fsdp2_step_220000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e83d20595491304c3c441f035f310137b31fcc72bd520ca6c0488c89427941f
+size 2769090643

stage3-local-terminal-step220000/fsdp2_step_220000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3626a1cfe5e3c34df9b97e8f33a01eb49166e3a308b6da675441c47f3e0b5c5f
+size 2769090643

stage3-local-terminal-step220000/fsdp2_step_220000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d764757b24c8bfe2a6c0fa683dc7f0a79f13b23a183b3c3dfbb1e86b5e445b3
+size 2769091588

stage3-local-terminal-step220000/fsdp2_step_220000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c55eccb454ba52acb5f8e6b25ffd535ed62a64f265c9f240ab4de5bcde81dd53
+size 2769098756

stage3-local-terminal-step220000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_220000

stage3-local-terminal-step220000/step_220000_info.json ADDED Viewed

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

+{
+  "tag": "step_220000",
+  "global_step": 220000,
+  "stage_start_step": 165617,
+  "skip_batches_hint": 54383,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3-local-terminal-step220000/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-step220000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3-local-terminal step_220000 raw resume checkpoint