Update models
Browse files- .gitattributes +13 -0
- DeepSeek-R1-Distill-Qwen-14B-Q2_K.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q3_K_L.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q3_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q3_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q4_0.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q4_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q5_0.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q5_K_M.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q5_K_S.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q6_K.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-Q8_0.gguf +3 -0
- DeepSeek-R1-Distill-Qwen-14B-f16.gguf +3 -0
- config.json +27 -0
.gitattributes
CHANGED
@@ -33,3 +33,16 @@ 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 |
+
DeepSeek-R1-Distill-Qwen-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
DeepSeek-R1-Distill-Qwen-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
DeepSeek-R1-Distill-Qwen-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
DeepSeek-R1-Distill-Qwen-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
DeepSeek-R1-Distill-Qwen-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
DeepSeek-R1-Distill-Qwen-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
DeepSeek-R1-Distill-Qwen-14B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
DeepSeek-R1-Distill-Qwen-14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
DeepSeek-R1-Distill-Qwen-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
DeepSeek-R1-Distill-Qwen-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
DeepSeek-R1-Distill-Qwen-14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
DeepSeek-R1-Distill-Qwen-14B-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
DeepSeek-R1-Distill-Qwen-14B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aebdb05b0d3329b2aac19ec2bf89251ad68ebf6ca91b53df52aabafaadcb589
|
3 |
+
size 5770497152
|
DeepSeek-R1-Distill-Qwen-14B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d08eb85ffac71a24ba00f832f8fe91ed55c440b62c3c4c03747fb6bb4f376f
|
3 |
+
size 7924767872
|
DeepSeek-R1-Distill-Qwen-14B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ab454758cd06aa98792091d97111678372c60a816e5ae81f13b274f6a6f5bca
|
3 |
+
size 7339203712
|
DeepSeek-R1-Distill-Qwen-14B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:875ec9309e9ae7486dff59786fba1885b4f34a9cdb53b09af574265084f857e2
|
3 |
+
size 6659595392
|
DeepSeek-R1-Distill-Qwen-14B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2286907126c0eae6e73dbaf7eb3165cf749f6c935c0851bf0d449cfa74ff7048
|
3 |
+
size 8517725312
|
DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:196cfaa9f9514295a569292b99a1103240796f94bbab5ef66be855ffd69a5f23
|
3 |
+
size 8988109952
|
DeepSeek-R1-Distill-Qwen-14B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cc02eb64bb1bc8dc38638bb6b797417a228fbf82c40d742ee9e9ad4dc5e5d58
|
3 |
+
size 8573430912
|
DeepSeek-R1-Distill-Qwen-14B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:455be56aebd4373622c798206d3f911dc0725c684fa8d574d3ef2dcde87dd8b5
|
3 |
+
size 10266553472
|
DeepSeek-R1-Distill-Qwen-14B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d30421cbfa4755eb0d647ee7054ef780c756fdfcc3f71ab851300bd274961fa7
|
3 |
+
size 10508872832
|
DeepSeek-R1-Distill-Qwen-14B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3a76fb117c00124ab49c56c0982ef5b55ac067cefd872504a94b7e1014df7a5
|
3 |
+
size 10266553472
|
DeepSeek-R1-Distill-Qwen-14B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f880e163f297b0084f7c30f7fff4bb5b9073d6b98b679b571a1b743a126e27ad
|
3 |
+
size 12124683392
|
DeepSeek-R1-Distill-Qwen-14B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08ed57a4824de6ab414095cd20b53e8dfd375dd953f940ffbe7340e5c9adb5f
|
3 |
+
size 15701597312
|
DeepSeek-R1-Distill-Qwen-14B-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c62652bb076e0ef440a02d23653bc3b4533b85c38a2cc165db98d010981a97e
|
3 |
+
size 29547715712
|
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": 151643,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 131072,
|
13 |
+
"max_window_layers": 48,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 48,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 131072,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.43.1",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_sliding_window": false,
|
26 |
+
"vocab_size": 152064
|
27 |
+
}
|