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")

# pip install -U transformers accelerate
# 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 31

Commit

0471020

verified ·

1 Parent(s): 9e97062

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3c-local-terminal-repeat2-step650000/all_config.yaml +46 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.0.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.1.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.2.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.3.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.4.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.5.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.6.pt +3 -0
stage3c-local-terminal-repeat2-step650000/carry_step_650000.7.pt +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/.metadata +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__0_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__1_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__2_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__3_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__4_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__5_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__6_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__7_0.distcp +3 -0
stage3c-local-terminal-repeat2-step650000/latest_checkpoint.txt +1 -0
stage3c-local-terminal-repeat2-step650000/step_650000_info.json +8 -0
stage3c-local-terminal-repeat2-step650000/train_metadata.yaml +13 -0
stage3c-local-terminal-repeat2-step650000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -780,3 +780,12 @@ stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__2_0.distcp filter=
 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3c-local-terminal-repeat2-step640000/fsdp2_step_640000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3c-local-terminal-repeat2-step650000/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-stage3c-local-terminal-repeat2-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-stage2c-hrm-full-nocap-repeat2-gbs180
+resume_step: null
+resume_step_offset: 631316
+run_name: KoHRM-Text-1.4B-stage3c-local-terminal-repeat2
+seed: 0
+skip_batches: 0
+total_steps_override: 700000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage3c-local-terminal-repeat2-step650000/carry_step_650000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:45bab1735acfbd091ad75b95d9fceb33ca26e6fe23f7a988eb6a539b680dfb14
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:92287621137cc7e7138b09fcf7086c355e2422dfdbfc87023d227ff5c0c733a3
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:00b85bca01c4340aad2d45112a20bed6e39b65010a536fe24d7f6378309eaf16
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b3effa1bcd078e9c3bc0247ee67889555c15bc125f8c428644e4e90638822b02
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2158d87a36acdb10fb5b97679fedd553ea869b42abe99ae1519eb1cb817895
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:57062a13a241881f0b6db4fa1673f397ec720ab6fa0d7cb4e37b8beed4a4a135
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f794fb333e9b5b9e9f86f52a19be7d90bd0c1b4a1cea8db263f62c471fc260
+size 1333

stage3c-local-terminal-repeat2-step650000/carry_step_650000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f05e0d1efc50da18473eafbca0cb5f09b1aca7683409842ae827e82cfb59d1
+size 1333

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8adf145703d956dae6fd5d912f45c73ea60bb581fca2751c41c07a26bec027
+size 983815

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:033cdf139949801c1b24c5f905ab712da724e91349efd681572f4f25a5cdece5
+size 2769065329

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:626c10e567b753452ef0c173a462d176d9e7bea2fe9a994c3940b80ffedca144
+size 2769090643

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ab30f57cc129ef36d8a645d44c704447df2b27ae7c24bbb78212bfe106d280
+size 2769090643

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:19d539458a6b4217e09795a33cfb94b9709f18d6650165b60edb77d936d616d9
+size 2769090643

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:72b36ad0513a096ec93305d1f7281bdeb80f95296b7b3eda2c02dfcd9f3f0748
+size 2769090643

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fde99a136792fa49e99151de8dd1f7de743938c9d6c659d84c9e72f018cc8234
+size 2769090643

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e951d8e3472841c04ab06864cabb1ebf53a4e50fe2b9017e77d9fc1d07d5414a
+size 2769091588

stage3c-local-terminal-repeat2-step650000/fsdp2_step_650000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b39b712cebcb153ac8f6978bea8d9da88a476b8bee5c852c400873bea9f9b58d
+size 2769098756

stage3c-local-terminal-repeat2-step650000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_650000

stage3c-local-terminal-repeat2-step650000/step_650000_info.json ADDED Viewed

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

+{
+  "tag": "step_650000",
+  "global_step": 650000,
+  "stage_start_step": 631316,
+  "skip_batches_hint": 18684,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3c-local-terminal-repeat2-step650000/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

stage3c-local-terminal-repeat2-step650000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3c-local-terminal-repeat2 step_650000 raw resume checkpoint