Text Generation
Transformers
GGUF
English
olmo2
Inference Endpoints
conversational
danielhanchen commited on
Commit
c10a156
·
verified ·
1 Parent(s): 86d960a

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,12 @@ 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
+ OLMo-2-0325-32B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ OLMo-2-0325-32B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ BF16/OLMo-2-0325-32B-Instruct-BF16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
39
+ OLMo-2-0325-32B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ OLMo-2-0325-32B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ OLMo-2-0325-32B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ OLMo-2-0325-32B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
43
+ OLMo-2-0325-32B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ BF16/OLMo-2-0325-32B-Instruct-BF16-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
BF16/OLMo-2-0325-32B-Instruct-BF16-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31db06bcd275b62ee2801715fc22d7f1c561556bf456d3e8933ffc4a2d307d5
3
+ size 49793239360
BF16/OLMo-2-0325-32B-Instruct-BF16-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83153834c232578e5dbaa2cae62bcf5533ca8bcccf4b1847eccde4e5ac581b08
3
+ size 14681011552
OLMo-2-0325-32B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b361f6957c5d84633a68360516ecf522dd0ec9c8da3ae6db87034d252b40ea55
3
+ size 12006374848
OLMo-2-0325-32B-Instruct-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d331d7cfd223e5b38ce6a88f4984cad8f9be60267c0e2e2178865ef5e95b1f02
3
+ size 12126797248
OLMo-2-0325-32B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b061b79d2005d3c358b844085bfa7d1d341a05c6e9bf17d64b47a2e6fbd1cb
3
+ size 15601434048
OLMo-2-0325-32B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbdd7c24bdef395ce81c81295802d7c061fc22aa119358c1d195a86b06dda40e
3
+ size 19482557888
OLMo-2-0325-32B-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90185573912d2bc2f7bb13facf0c123738b36d5db86ba6eefaaea99ab756ee3
3
+ size 22860283328
OLMo-2-0325-32B-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3255550a4b45375840f567fba96148214ee47ef8e0b89cb953418b28d2b371d2
3
+ size 26449116608
OLMo-2-0325-32B-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfeadee9291508787a95127298fdb430b43f23346f67b8c7c154d450f16c8fd2
3
+ size 34255601088
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "olmo2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 100277,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 500000,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.50.0.dev0",
25
+ "unsloth_fixed": true,
26
+ "use_cache": false,
27
+ "vocab_size": 100352
28
+ }