Marko Tasic commited on
Commit
0dba3d8
1 Parent(s): 9a24edf

model and eval

Browse files
evaluate-leaderboard/results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78254552d8f53072000de0507f1a2390c56c95d123ecc2c3958d8eb58cb88c9
3
+ size 459390489
evaluate-long/results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8162d60047a666c1339fccfc43dccd1a14adeb1d1e1e60cc5f60cb4dda5cc1ff
3
+ size 6215150
evaluate-math/results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc983fda4b78342ef3d53755c811b4bad968a7a3e4a2dc9ef1d40f0741fd935
3
+ size 24224926
evaluate-quick/results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f136b6228db93f37def600454d5367af360ff536fd4cae434d5b9f504bc21c5
3
+ size 138877268
evaluate-reasoning/results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e0695eb46b0f11f545ec6a9f6499097bbaa455e5ec007d2d17e15ead8e7f55
3
+ size 211984784
model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96e42fc698b2dea9b935c626495088ae587839095b175fa6049aa98748bd44e
3
+ size 309363358
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5203c97f565f0006f8891d15994a3b8ab98dbc05615e905f680745c2d79cf901
3
+ size 309357832
out/converted_model/config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tangledgroup/tangled-llama-33m-32k-base-v0.1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_size": 1024,
9
+ "intermediate_size": 4096,
10
+ "max_position_embeddings": 38400,
11
+ "model_type": "llama",
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 5,
14
+ "num_key_value_heads": 8,
15
+ "rms_norm_eps": 1e-05,
16
+ "rope_scaling": null,
17
+ "tie_word_embeddings": false,
18
+ "torch_dtype": "bfloat16",
19
+ "transformers_version": "4.44.2",
20
+ "use_cache": true,
21
+ "vocab_size": 38400
22
+ }
out/converted_model/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96e42fc698b2dea9b935c626495088ae587839095b175fa6049aa98748bd44e
3
+ size 309363358
out/converted_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5203c97f565f0006f8891d15994a3b8ab98dbc05615e905f680745c2d79cf901
3
+ size 309357832
out/pretrain/final/config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tangledgroup/tangled-llama-33m-32k-base-v0.1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_size": 1024,
9
+ "intermediate_size": 4096,
10
+ "max_position_embeddings": 38400,
11
+ "model_type": "llama",
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 5,
14
+ "num_key_value_heads": 8,
15
+ "rms_norm_eps": 1e-05,
16
+ "rope_scaling": null,
17
+ "tie_word_embeddings": false,
18
+ "torch_dtype": "bfloat16",
19
+ "transformers_version": "4.44.2",
20
+ "use_cache": true,
21
+ "vocab_size": 38400
22
+ }