Hugging Face's logo

gaianet
/
Megrez-3B-Instruct-GGUF

Text Generation
GGUF
English
Chinese
llama
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
345ff2b
•
1 Parent(s): bb6b77d

Update models

Browse files
Files changed (15) hide show
  1. .gitattributes +13 -0
  2. Megrez-3B-Instruct-Q2_K.gguf +3 -0
  3. Megrez-3B-Instruct-Q3_K_L.gguf +3 -0
  4. Megrez-3B-Instruct-Q3_K_M.gguf +3 -0
  5. Megrez-3B-Instruct-Q3_K_S.gguf +3 -0
  6. Megrez-3B-Instruct-Q4_0.gguf +3 -0
  7. Megrez-3B-Instruct-Q4_K_M.gguf +3 -0
  8. Megrez-3B-Instruct-Q4_K_S.gguf +3 -0
  9. Megrez-3B-Instruct-Q5_0.gguf +3 -0
  10. Megrez-3B-Instruct-Q5_K_M.gguf +3 -0
  11. Megrez-3B-Instruct-Q5_K_S.gguf +3 -0
  12. Megrez-3B-Instruct-Q6_K.gguf +3 -0
  13. Megrez-3B-Instruct-Q8_0.gguf +3 -0
  14. Megrez-3B-Instruct-f16.gguf +3 -0
  15. config.json +31 -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
+ Megrez-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Megrez-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Megrez-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Megrez-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Megrez-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Megrez-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Megrez-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Megrez-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Megrez-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Megrez-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Megrez-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Megrez-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Megrez-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
Megrez-3B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e80be86bcc1ba8d55502e08e21e2b3773f596a6942c58c9ee17feb8c1d0d80
3
+ size 1210225952
Megrez-3B-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3910bb4bff43e9dfd24a2399de72e9df4e4d96c89e56485edeb6d2c867a0a2
3
+ size 1600083232
Megrez-3B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25f6595ec301e19fa891136ba9fca4532637d7175f0a4a58b3cac0d74981c45
3
+ size 1498912032
Megrez-3B-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7073c289c9ac12bf5996a5403c7527089ddf515396cfaa00d1900699fcde573
3
+ size 1381111072
Megrez-3B-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fdc5027a56e5ee67959e1936449a9b33ec66576de5a707210eb7620b882c90
3
+ size 1726485792
Megrez-3B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad234df7dd4083d782c6a5c728cf57712d5a6a45e0c0f2b844e17df3db326c13
3
+ size 1808938272
Megrez-3B-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb03fa4b3ac5538aefae5470a7246cf2f544e37bb77c055636cea0c5b3b71b58
3
+ size 1736480032
Megrez-3B-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8481ba580d2269fbe944f914b8cf550b8febfaa924f284ec295f5813f870c86b
3
+ size 2051544352
Megrez-3B-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15a33cbedfd418a0df6b2a06d4e3ba415b59853942477b1b407a36d2c111155
3
+ size 2094019872
Megrez-3B-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74436104b795e4afcb2564aea7344667b9da3493ff3ff513dcc0e49ea6ece7e
3
+ size 2051544352
Megrez-3B-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb97f1ee7bdb1dc489320a30959958fc035c85d97c9ce000fdc3c79c08c8d8f5
3
+ size 2396919072
Megrez-3B-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6eef13671f94ae70d09d3e5538c5f4e552facc8b83eca0c52d11ad2f7eaa09
3
+ size 3102905632
Megrez-3B-Instruct-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d829867730264d0c9629853dbb6a2cf921fa29f6bfb2ff706ba57c0b9f6e0c25
3
+ size 5835756832
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Megrez-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": null,
9
+ "eos_token_id": 120005,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 7168,
14
+ "max_position_embeddings": 32768,
15
+ "max_sequence_length": 32768,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 40,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 10,
21
+ "pad_token_id": 120002,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 5000000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.43.4",
29
+ "use_cache": true,
30
+ "vocab_size": 122880
31
+ }