Hugging Face's logo

locuslab
/
ift_gsm-smollm2-1.7b-all_raw_folders_meta-600B-metamix3p-1k-0

Safetensors
llama
model
transformer
smollm2
Model card Files Community
saching0071 commited on
Commit
e4412f4
·
verified ·
1 Parent(s): 16f222d

Upload model version: final

Browse files
Files changed (5) hide show
  1. README.md +2 -16
  2. config.json +1 -1
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- version: main
3
  family: smollm2-1.7b
4
  model_name: -all_raw_folders_meta-600B-metamix3p-1k-0
5
  license: mit
@@ -8,7 +8,7 @@ tags:
8
  - transformer
9
  - smollm2
10
  ---
11
- # SmolLM2 -all_raw_folders_meta-600B-metamix3p-1k-0 (Version: main)
12
 
13
  ## Model Details
14
  - **Architecture:** SmolLM2
@@ -30,17 +30,3 @@ train:
30
  micro_batch_size: 8
31
 
32
  ```
33
-
34
- ## Model Loading and Revision System
35
-
36
- This repository hosts multiple revisions of the model.
37
- To load a specific revision, use the `revision` parameter. For example:
38
-
39
- ```python
40
- from transformers import AutoModelForCausalLM, AutoTokenizer
41
-
42
- model = AutoModelForCausalLM.from_pretrained("locuslab/-all_raw_folders_meta-600B-metamix3p-1k-0", revision="final")
43
- tokenizer = AutoTokenizer.from_pretrained("locuslab/-all_raw_folders_meta-600B-metamix3p-1k-0", revision="final")
44
- ```
45
-
46
- Replace `"final"` with the desired revision.
 
1
  ---
2
+ version: final
3
  family: smollm2-1.7b
4
  model_name: -all_raw_folders_meta-600B-metamix3p-1k-0
5
  license: mit
 
8
  - transformer
9
  - smollm2
10
  ---
11
+ # SmolLM2 -all_raw_folders_meta-600B-metamix3p-1k-0 (Version: final)
12
 
13
  ## Model Details
14
  - **Architecture:** SmolLM2
 
30
  micro_batch_size: 8
31
 
32
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/project/flame/sachingo/shared_assets/out/mix_ift_v8/v8_models/smollm2-1.7b/base-smollm2-1.7b-all_raw_folders_metadata-600B-lr2e-05-gbs16-metamix3p-1k-100",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/tmp/sachin_temp/shared_assets/out/mix_ift_v8/v8_models/smollm2-1.7b/base-smollm2-1.7b-all_raw_folders_meta-600B-mbs8-gbs1024-17feb-lr2e-05-gbs16-metamix3p-1k-0",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:841319d97ecbef7ec6743a93bad7a2b902ad45dbce5058de9796e12a8dc1953b
3
  size 4999906800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a9f7c0c50c1f2127ac3c31fc4c8bff9e076e8584026e99adcbb3453590aef3
3
  size 4999906800
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff575f99cd528787845021272bf5ffa526a320d05836acc5ee4b6177fc2fda95
3
  size 2248277040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d95f5cc0d2e91822dfac695b29388b9ad541e00981cd8f78c05a5717acd45b1
3
  size 2248277040
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1279f3bd08e857e0871cda275e223eca0101a6945b11bbfe9e5e354cb67a6760
3
  size 5944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a3b9b7c6167bb6042f5ecd7825968f38c41020550dc0e2dfa3dc1522a85d83
3
  size 5944