Hugging Face's logo

flyingbugs
/
Qwen2.5-Math-7B-Instruct-keep-0.4-end-start-0.5-eos

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Model card Files
xet
Community
flyingbugs commited on
Commit
79233c6
·
verified ·
1 Parent(s): 9b80122

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. config.json +3 -3
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. training_args.bin +1 -1
config.json CHANGED
@@ -9,7 +9,7 @@
9
  "hidden_size": 3584,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 18944,
12
- "max_position_embeddings": 4096,
13
  "max_window_layers": 28,
14
  "model_type": "qwen2",
15
  "num_attention_heads": 28,
@@ -17,8 +17,8 @@
17
  "num_key_value_heads": 4,
18
  "rms_norm_eps": 1e-06,
19
  "rope_scaling": null,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.50.3",
 
9
  "hidden_size": 3584,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 18944,
12
+ "max_position_embeddings": 32768,
13
  "max_window_layers": 28,
14
  "model_type": "qwen2",
15
  "num_attention_heads": 28,
 
17
  "num_key_value_heads": 4,
18
  "rms_norm_eps": 1e-06,
19
  "rope_scaling": null,
20
+ "rope_theta": 300000.0,
21
+ "sliding_window": null,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.50.3",
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:571562d7552fdbedad29df6e1d5149d0effb8b20768688910d104af07745842a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a5382dc68cc8b61d4616554f79a77ba83e011e767531b4f2aa77108fc08b29
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27d0a427e14709ddf840e625f8fdd395055e88383c38c7ff25e76eb5d0e219db
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793ca454cd200f9dcaeefcd7cec99afba44c4a70bb4749c5e9ff80ffad22a7e9
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb914324170834f0fd80061e6bed570083aee31c4eba7d39009db5e76eecf6f0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8f378470bd715304624086914e759faa8fb040d980b3460a0ebede5897159c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76fa38134c829da12cf628ab1ba895b03702c2476aab2973da2d4b7ea2952878
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48bd5ff08625d986098ad54bff548d013056f1f8c43a7b7a025caa68aa85dc0
3
  size 1089994880
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62b8e0525450f07b95ae74ee0b614e4b30085534c523941cdb176744996280ca
3
  size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3add45ffd39eba98e2b412d4a3bd8303f5d253ccb0fc0ad9bd759006d44ab0
3
  size 7544