Hugging Face's logo

distillslm
/
alpaca_seq_kd_sft_Qwen2.5-3B-Instruct_from_Qwen2.5-7B-Instruct

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
gkd
conversational
text-generation-inference
Model card Files Community
yuzhounie commited on
Commit
2c3aa38
·
verified ·
1 Parent(s): e2a9cf9

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +2 -2
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. tokenizer.json +1 -1
  5. training_args.bin +2 -2
config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
- "sliding_window": null,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.48.2",
26
  "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
 
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
+ "sliding_window": 32768,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.49.0",
26
  "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:288a66ed8949e7962f28006a4a759d517cd279038e2fde27f46a78098685fba0
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbecb29f75b42855f45667e9d1b7c215d5bf531bebeddc2cfa5a575b62b92d18
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d5e66172313fd821ce6e2b68969bd1979c42e793d948f479e1f1a5c6393d91
3
  size 1214366696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71221f92ea5e0dd8924e20eb87ecfae298f0c9c30dff1468a4ca9bb32633f817
3
  size 1214366696
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:092cfd5bd5236e921bbc94a3a03d2b4371aa7e0ad4c87ef9ea945ae6beb76f15
3
  size 11421994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63efe5c30bba9df6d3cc9279d0fb0f1d18ae0593bf8981e8548c4d043ca0c16e
3
  size 11421994
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44086ac79cc5eb8ddc28b12f1721efe63442a1d948abdacce50262be28d70b8a
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b68cc1054aee25c8399bbf59f61d1387d9f0bdfc295b303db19f25f12f5a4e
3
+ size 7288