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
- Transformers
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
Add files using upload-large-folder tool
Browse files- .gitattributes +9 -0
- stage2c-hrm-full-nocap-repeat2-step590000/all_config.yaml +46 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.0.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt +1 -0
- stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json +8 -0
- stage2c-hrm-full-nocap-repeat2-step590000/train_metadata.yaml +13 -0
- stage2c-hrm-full-nocap-repeat2-step590000/upload_manifest.json +1 -0
.gitattributes
CHANGED
|
@@ -708,3 +708,12 @@ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp filter=
|
|
| 708 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 709 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 710 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 708 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 709 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 710 |
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 711 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 712 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 713 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 714 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 715 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 716 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 717 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 718 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 719 |
+
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
stage2c-hrm-full-nocap-repeat2-step590000/all_config.yaml
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
arch:
|
| 2 |
+
H_cycles: 2
|
| 3 |
+
H_override: {}
|
| 4 |
+
L_cycles: 3
|
| 5 |
+
bp_max_steps: 5
|
| 6 |
+
bp_warmup_ratio: 0.2
|
| 7 |
+
expansion: 4
|
| 8 |
+
half_layers: true
|
| 9 |
+
head: lm_head@LMHead
|
| 10 |
+
hidden_size: 1536
|
| 11 |
+
init_type: lecun_normal
|
| 12 |
+
n_layers: 32
|
| 13 |
+
name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
|
| 14 |
+
norm_eps: 1.0e-06
|
| 15 |
+
norm_type: pre
|
| 16 |
+
num_heads: 12
|
| 17 |
+
pos_emb_type: rope
|
| 18 |
+
rope_theta: 10000.0
|
| 19 |
+
beta1: 0.9
|
| 20 |
+
beta2: 0.95
|
| 21 |
+
checkpoint_interval: 1
|
| 22 |
+
checkpoint_keep_last: 2
|
| 23 |
+
checkpoint_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2-gbs180
|
| 24 |
+
checkpoint_step_interval: 10000
|
| 25 |
+
data:
|
| 26 |
+
path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1
|
| 27 |
+
target_only: true
|
| 28 |
+
ema: 0.9999
|
| 29 |
+
epochs: 1
|
| 30 |
+
fwd_bwd_dtype: bfloat16
|
| 31 |
+
global_batch_size: 180224
|
| 32 |
+
log_interval: 5
|
| 33 |
+
lr: 0.00022
|
| 34 |
+
lr_min_ratio: 1.0
|
| 35 |
+
lr_warmup_steps: 2000
|
| 36 |
+
project_name: KoHRM-Text
|
| 37 |
+
resume_epoch: null
|
| 38 |
+
resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1c-hrm-fastcap-repeat2-gbs180
|
| 39 |
+
resume_step: null
|
| 40 |
+
resume_step_offset: 550699
|
| 41 |
+
run_name: KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2
|
| 42 |
+
seed: 0
|
| 43 |
+
skip_batches: 0
|
| 44 |
+
total_steps_override: 700000
|
| 45 |
+
weight_decay: 0.1
|
| 46 |
+
weights_only_resume_from_ema: false
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5725b1c387d769870ee247d66d644856de4f414c6028a43b8b831e4f416942f2
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4bc44d89cd6baf153cf40a385fa3a7626c96f54c4383f0904c96e535fe2cdfe
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e2a1e577fea76e7c3cf73fe2c0db8fd0de37728a2b1a05ded2190bb5c91101
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8206d5c40f00a09247b1e8af38584c630a246352e525ea8d354b14178f3697e4
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c86553a7c52f4228de77b25e21e79723bb967c7fc972bb1c6a46e10e96377c7b
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c776002f3c55db0d1944baa3b5af451d7e841463c6806ddd1b81026cb2042164
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e271413c5f589106bee9d649c01b32299da9396cf7fd241822a7234777442b2
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3a2cde857e21576a0611366c0f11cc8fbced20ecf504ecb80d624d9c9686482
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0992f844ba808553761f04e30dc3352e79e54a0d1297f268ead6892d2ae5e735
|
| 3 |
+
size 983815
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0f2ea1a8dfd4b42594448ced0753f1b7c71aed6a7deb8c55794c5727e08a76f
|
| 3 |
+
size 2769065329
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:626dca18022e89e130c34ba6b433eccc088994e58d13ff4d7748ce00de830dfc
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bddb19b49d5a6fa6982517b20f0781def9d3cce07d62d195f4fff56e012df655
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bba7d216474b560ea98c6d821deeb77f5e1ffaadf085062dfab2167b68ca8e4
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48562f50462dda92664c19ec01e0aff2c697c4a4be870beee41344956e2e4131
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b542f7d60015e75687969436a41367090ee3ec8e763c673c160481de2128431f
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d397b5b7925b1458cccbbbbeefb0e53d7e34adcccaa990720bad00dfa580c406
|
| 3 |
+
size 2769091588
|
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54a0dabddce84b6fa33779474874694524a9f631812b2e2d44c8dad647319dbc
|
| 3 |
+
size 2769098756
|
stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
step_590000
|
stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_590000",
|
| 3 |
+
"global_step": 590000,
|
| 4 |
+
"stage_start_step": 550699,
|
| 5 |
+
"skip_batches_hint": 39301,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage2c-hrm-full-nocap-repeat2-step590000/train_metadata.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_seq_len: 4096
|
| 2 |
+
tokenizer_info:
|
| 3 |
+
boq: <|im_start|>
|
| 4 |
+
condition_mapping:
|
| 5 |
+
cot: <|object_ref_end|>
|
| 6 |
+
direct: <|object_ref_start|>
|
| 7 |
+
noisy: <|quad_start|>
|
| 8 |
+
synth: <|quad_end|>
|
| 9 |
+
eoa: <|box_end|>
|
| 10 |
+
eoq: <|im_end|>
|
| 11 |
+
tokenizer_path: /home/work/.data/huggingface/trained_tokenizers/hrm-ko-terminal-131k-v1/tokenizer.json
|
| 12 |
+
total_length: 14553653061
|
| 13 |
+
vocab_size: 131072
|
stage2c-hrm-full-nocap-repeat2-step590000/upload_manifest.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
stage2c-hrm-full-nocap-repeat2 step_590000 raw resume checkpoint
|