apepkuss79 commited on
Commit
96a89d1
1 Parent(s): 935b958

Update models

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ Qwen2.5-1.5B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-1.5B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-1.5B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-1.5B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-1.5B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-1.5B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-1.5B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-1.5B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-1.5B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-1.5B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-1.5B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-1.5B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-1.5B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3d8542182ba31d4a1a5b8c4ff7d0488b7798deb71b5fa51cb728021b84ddbc
3
+ size 676304896
Qwen2.5-1.5B-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce2be6e4a9c3e3501a2f41e884c33b6a119c446250d050f2746a264920b8c59
3
+ size 880162816
Qwen2.5-1.5B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc118d0949407aaf662c95e5895c1f7801b2050f40e83e7d06e798817017ce07
3
+ size 824178688
Qwen2.5-1.5B-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e056ca0b802d5412c40432821c201e4f4d5ed9518d69cfeb6a994a2eb438676c
3
+ size 760944640
Qwen2.5-1.5B-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2887331c6e01f2a0fd7163daa5062353fe8939844d83aee69847d4fc842dfe7e
3
+ size 934955008
Qwen2.5-1.5B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffcf166d3467df1c38991fa6196c8798b7e2bb9101d8fa34f6cd3c186913f14
3
+ size 986048512
Qwen2.5-1.5B-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5d2141a8fdd863c78cf19ac448a78ad972bfa54c989cd35c845cf032483b06
3
+ size 940312576
Qwen2.5-1.5B-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ddd7e4215aa4e812831791d13df4b4a2260278ae2cc222acb03f098c773e9a
3
+ size 1098729472
Qwen2.5-1.5B-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20c4b91eedc93c1343d1038e5d581cc256b1cac3d03171ec9c66ab525f83a94
3
+ size 1098729472
Qwen2.5-1.5B-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46baaa4173a5cf6be8f9b0851afc9756da163253fa6da1b413f4db189827df57
3
+ size 1272739840
Qwen2.5-1.5B-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144ea9981a90447fb1dbbd8f0a872e3dea0f6eed3db2adde402f22b752ea1caa
3
+ size 1646573056
Qwen2.5-1.5B-Instruct-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9e80eacde5690a3a3cf6afcf44a3d53cdab6e0b777552fb64f055efc658956
3
+ size 3093669376
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 21,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 32768,
21
+ "tie_word_embeddings": true,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 151936
27
+ }