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
- 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 filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +11 -0
- README.md +7 -0
- stage1-gbs180/all_config.yaml +45 -0
- stage1-gbs180/carry_step_10000.0.pt +3 -0
- stage1-gbs180/carry_step_10000.1.pt +3 -0
- stage1-gbs180/carry_step_10000.2.pt +3 -0
- stage1-gbs180/carry_step_10000.3.pt +3 -0
- stage1-gbs180/carry_step_10000.4.pt +3 -0
- stage1-gbs180/carry_step_10000.5.pt +3 -0
- stage1-gbs180/carry_step_10000.6.pt +3 -0
- stage1-gbs180/carry_step_10000.7.pt +3 -0
- stage1-gbs180/carry_step_15000.0.pt +3 -0
- stage1-gbs180/carry_step_15000.1.pt +3 -0
- stage1-gbs180/carry_step_15000.2.pt +3 -0
- stage1-gbs180/carry_step_15000.3.pt +3 -0
- stage1-gbs180/carry_step_15000.4.pt +3 -0
- stage1-gbs180/carry_step_15000.5.pt +3 -0
- stage1-gbs180/carry_step_15000.6.pt +3 -0
- stage1-gbs180/carry_step_15000.7.pt +3 -0
- stage1-gbs180/carry_step_20000.0.pt +3 -0
- stage1-gbs180/carry_step_20000.1.pt +3 -0
- stage1-gbs180/carry_step_20000.2.pt +3 -0
- stage1-gbs180/carry_step_20000.3.pt +3 -0
- stage1-gbs180/carry_step_20000.4.pt +3 -0
- stage1-gbs180/carry_step_20000.5.pt +3 -0
- stage1-gbs180/carry_step_20000.6.pt +3 -0
- stage1-gbs180/carry_step_20000.7.pt +3 -0
- stage1-gbs180/carry_step_25000.0.pt +3 -0
- stage1-gbs180/carry_step_25000.1.pt +3 -0
- stage1-gbs180/carry_step_25000.2.pt +3 -0
- stage1-gbs180/carry_step_25000.3.pt +3 -0
- stage1-gbs180/carry_step_25000.4.pt +3 -0
- stage1-gbs180/carry_step_25000.5.pt +3 -0
- stage1-gbs180/carry_step_25000.6.pt +3 -0
- stage1-gbs180/carry_step_25000.7.pt +3 -0
- stage1-gbs180/fsdp2_step_10000/.metadata +3 -0
- stage1-gbs180/fsdp2_step_10000/__0_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__1_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__2_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__3_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__4_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__5_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__6_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_10000/__7_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_15000/__4_0.distcp +3 -0
- stage1-gbs180/fsdp2_step_15000/__6_0.distcp +3 -0
- stage1-gbs180/step_10000_info.json +8 -0
- stage1-gbs180/step_15000_info.json +8 -0
- stage1-gbs180/step_20000_info.json +8 -0
- stage1-gbs180/step_25000_info.json +8 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
stage1-gbs180/fsdp2_step_10000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
stage1-gbs180/fsdp2_step_10000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
stage1-gbs180/fsdp2_step_10000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
stage1-gbs180/fsdp2_step_10000/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
stage1-gbs180/fsdp2_step_10000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
stage1-gbs180/fsdp2_step_10000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
stage1-gbs180/fsdp2_step_10000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
stage1-gbs180/fsdp2_step_10000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
stage1-gbs180/fsdp2_step_10000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
stage1-gbs180/fsdp2_step_15000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
stage1-gbs180/fsdp2_step_15000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# KoHRM-Text-1.4B Raw Checkpoints
|
| 2 |
+
|
| 3 |
+
Raw FSDP2 checkpoints for training resume. These files are intentionally separated from the main model repo because Hugging Face may flag DCP shard files as unsafe for normal model loading.
|
| 4 |
+
|
| 5 |
+
- stage: stage1-gbs180
|
| 6 |
+
- available steps: 10000, 15000, 20000, 25000
|
| 7 |
+
- main safe model repo: LLM-OS-Models/KoHRM-Text-1.4B
|
stage1-gbs180/all_config.yaml
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1-hrm-fastcap-gbs180
|
| 23 |
+
checkpoint_step_interval: 5000
|
| 24 |
+
data:
|
| 25 |
+
path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1
|
| 26 |
+
target_only: true
|
| 27 |
+
ema: 0.9999
|
| 28 |
+
epochs: 1
|
| 29 |
+
fwd_bwd_dtype: bfloat16
|
| 30 |
+
global_batch_size: 180224
|
| 31 |
+
log_interval: 5
|
| 32 |
+
lr: 0.00022
|
| 33 |
+
lr_min_ratio: 1.0
|
| 34 |
+
lr_warmup_steps: 2000
|
| 35 |
+
project_name: KoHRM-Text
|
| 36 |
+
resume_epoch: null
|
| 37 |
+
resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage0b-debug-launch2
|
| 38 |
+
resume_step: null
|
| 39 |
+
resume_step_offset: 7765
|
| 40 |
+
run_name: KoHRM-Text-1.4B-stage1-hrm-fastcap-gbs180
|
| 41 |
+
seed: 0
|
| 42 |
+
skip_batches: 0
|
| 43 |
+
total_steps_override: 88522
|
| 44 |
+
weight_decay: 0.1
|
| 45 |
+
weights_only_resume_from_ema: false
|
stage1-gbs180/carry_step_10000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dab378260628dcc41db9ff1f116901964966061288558610b97b997f39543720
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:375b8f9a8608bf736738aa99fa81465f9b12836adf1e0732eb961db413a5608f
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f60eb95cd0cfa79ee73bc0c6c833bd174f67fd5e03500f0878290c7697235d1
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5ba80edc79155bd8ebdb04f0e3f181400566db20cdc2daf33af4c227852a39a
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:311783bef37a35511f2013a0b5c16214b1bef8f6377d63725795025f0922c2e5
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cf032c4cf2fb25122fbd87e8f7af1993778889c1ceffc4034b14fe27375dcce
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca3f394becf9931201d61bb85ae2fcccab4ceea8ed7e563b96b71cac8b881d5e
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_10000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63855aa3d1338c0539f03934a44e379043e26efc0c6dfef41e84ba9c50e0b62d
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95bdeec6bd68ee8d6f79bb2401ba9fd14426d14e964147647da3fc83b0876caf
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22ab8b08877e42887a6b543a5a36c3d8e90d56254ee2a9d57d32b18239574026
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c145abb6ef679c699dc6e1879d708252f6829f28902049b5c017f0eb90f07a
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6ebad8c38062402800dc6cd15b825d601a1c41538c4907856163b84f84b4cf
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd8d6eb70214f001bfc9ac8b6362ea69f2d4fe91596bf021d07db9e01ca979c
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01fc6b242e53fe50d98dcc67dc118557f231a2c3e795a9b8ed60159d15e28b4c
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce884de03a2d9e9aeabcbe244b75f275a222b05bccd2224eb02607b238d1648f
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_15000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cb6a2288fe6135e797825f00eb6d5dafc6883c2d2c7d2473b7c22382b82ba50
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b364353e1bb5f14b6bacd5ca66a9dfa51d55d90958261fc37744a9fcd87b1b1f
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2cfe87fdcc18d9901ae86f16294c7330695c96114f110715acfa9847a11995
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9d046cae2239607ed4b00aa2032e086d7302767c294946ecdaf94707001ec6
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2f1ffa92c171b180407bfe45c3c2931ba3c63ba8b0bc373431053153e6580b4
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:866375fa08b1fa67df79a368d47ed7e67dfbfd2ba3c8cb76fbabff90502cba21
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f998a8127b4b5a567669d2a0b37743a41b24fea04ad6c28a9dc924e13483719f
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0b37c0b444f6e20545af80590b48f2e51a3d4990b14f86753cf69b9eeb61372
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_20000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f074d7c528d0eceb615a0a7e6453941f3fba69f4f40ea955af3795ebb2b3e38d
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00f739b64eb13b0c443aee82d76a5fc865c82b0e6e371d1f9c938a3c71c0a643
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43ce1f40b823c0f132e496e72f5eb4116d53725bdfb4b84adbe7c3a1873950e7
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d833323b299383830482a8c19fac63bb61dfe3206535bd206d8f7a246b4ba7a4
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bfa8a4e8a87054853886cafcd26959e67f6f6298e381ba58f0cf948ae6dabb1
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e0cd377accb93db1732a008054d109b77b5d66e3525ab84fa48d6ba462696e
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caebc4381f62ce2a9194f5f6c6ad30df7066ecec8e319c471f247607d7934e0f
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:333014deed66cb1fe60680d4dbed8a77ffa24cd21410d4e58eb099d907b6f397
|
| 3 |
+
size 1327
|
stage1-gbs180/carry_step_25000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9a55d28492838d1b18c75453d457118bd9a650ce282814198b589107d41e924
|
| 3 |
+
size 1327
|
stage1-gbs180/fsdp2_step_10000/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e8493667e421add1f4f2d485ebb5763bdad456c9236bf8ee8d6dd527a6f8c9
|
| 3 |
+
size 983802
|
stage1-gbs180/fsdp2_step_10000/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87e9846b8e74c33006787d96dbd8b7cdeabb0aa54bba763a766a8ce0cd26b67a
|
| 3 |
+
size 2769065329
|
stage1-gbs180/fsdp2_step_10000/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac20d0adde97f47009e1376dd39574c658f5d817a42842dc279909daa0d4e2f
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_10000/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16cf1de977fc30582f871cc33911ead3b7c025c9ebc19cf3d70f8c91e368c861
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_10000/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ab8447aec711c830a0c977085dbd86b6b4c662afe98fc660634d5ee47e28326
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_10000/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:413d51d51c1c191f6a5ceb5881f36c6db0ca206fc1deb22602aa3dcde87b5b81
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_10000/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da4fd0c186ddd268de0e889eb9d67afc96f2895ca9e9ad4f7a2a99b664178880
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_10000/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea16f17f202ad52a9c49e8ab5c61e02b84d6e78b14e6a593dc68d689a60c7b12
|
| 3 |
+
size 2769091588
|
stage1-gbs180/fsdp2_step_10000/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2745c90ed50dafb5eaf12bf7f2c62ced6752cf5e137350a515593fd92f906bd
|
| 3 |
+
size 2769098756
|
stage1-gbs180/fsdp2_step_15000/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c61709ce968c2a3dadca65cddcf6e4f96d1f4323f7a5ee050b1dbada40fd14
|
| 3 |
+
size 2769090643
|
stage1-gbs180/fsdp2_step_15000/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3efb3df29979c73a4cd33cb9bdd346e24e9df9f0d87a8a0539111190e4b944d4
|
| 3 |
+
size 2769091588
|
stage1-gbs180/step_10000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_10000",
|
| 3 |
+
"global_step": 10000,
|
| 4 |
+
"stage_start_step": 7765,
|
| 5 |
+
"skip_batches_hint": 2235,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage1-gbs180/step_15000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_15000",
|
| 3 |
+
"global_step": 15000,
|
| 4 |
+
"stage_start_step": 7765,
|
| 5 |
+
"skip_batches_hint": 7235,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage1-gbs180/step_20000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_20000",
|
| 3 |
+
"global_step": 20000,
|
| 4 |
+
"stage_start_step": 7765,
|
| 5 |
+
"skip_batches_hint": 12235,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage1-gbs180/step_25000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_25000",
|
| 3 |
+
"global_step": 25000,
|
| 4 |
+
"stage_start_step": 7765,
|
| 5 |
+
"skip_batches_hint": 17235,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|