GGUF
DataSoul commited on
Commit
2d23d5d
1 Parent(s): 70eae9b

Upload 3 files

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ALMA-7B-R-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
  ALMA-7B-R-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ALMA-7B-R-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
  ALMA-7B-R-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ ALMA-7B-R-imatrix-f16.dat filter=lfs diff=lfs merge=lfs -text
ALMA-7B-R-imatrix-f16.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ec6c7628707c3be880869495d4e2660b13088906afb0c0eaa7d72285d4c5b3
3
+ size 4562142
ALMA-preset - cte.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "常用ALMA-en译中",
3
+ "load_params": {
4
+ "n_ctx": 4000,
5
+ "n_batch": 512,
6
+ "rope_freq_base": 10000,
7
+ "rope_freq_scale": 1,
8
+ "n_gpu_layers": 60,
9
+ "use_mlock": true,
10
+ "main_gpu": 0,
11
+ "tensor_split": [
12
+ 0
13
+ ],
14
+ "seed": -1,
15
+ "f16_kv": true,
16
+ "use_mmap": true
17
+ },
18
+ "inference_params": {
19
+ "n_threads": 4,
20
+ "n_predict": -1,
21
+ "top_k": 40,
22
+ "top_p": 0.6,
23
+ "temp": 0.9,
24
+ "repeat_penalty": 1.1,
25
+ "input_prefix": "\nEnglish:",
26
+ "input_suffix": "\nChinese:",
27
+ "antiprompt": [
28
+ ],
29
+ "pre_prompt": "Translate this from English to Chinese.",
30
+ "pre_prompt_prefix": "",
31
+ "pre_prompt_suffix": "",
32
+ "seed": -1,
33
+ "tfs_z": 1,
34
+ "typical_p": 1,
35
+ "repeat_last_n": 64,
36
+ "frequency_penalty": 0,
37
+ "presence_penalty": 0,
38
+ "n_keep": 0,
39
+ "logit_bias": {},
40
+ "mirostat": 0,
41
+ "mirostat_tau": 5,
42
+ "mirostat_eta": 0.1,
43
+ "memory_f16": true,
44
+ "multiline_input": false,
45
+ "penalize_nl": true
46
+ }
47
+ }
ALMA-preset - etc.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "常用ALMA-中译en",
3
+ "load_params": {
4
+ "n_ctx": 4000,
5
+ "n_batch": 512,
6
+ "rope_freq_base": 10000,
7
+ "rope_freq_scale": 1,
8
+ "n_gpu_layers": 60,
9
+ "use_mlock": true,
10
+ "main_gpu": 0,
11
+ "tensor_split": [
12
+ 0
13
+ ],
14
+ "seed": -1,
15
+ "f16_kv": true,
16
+ "use_mmap": true
17
+ },
18
+ "inference_params": {
19
+ "n_threads": 4,
20
+ "n_predict": -1,
21
+ "top_k": 40,
22
+ "top_p": 0.6,
23
+ "temp": 0.9,
24
+ "repeat_penalty": 1.1,
25
+ "input_prefix": "\nChinese:",
26
+ "input_suffix": "\nEnglish:",
27
+ "antiprompt": [
28
+ ],
29
+ "pre_prompt": "Translate this from Chinese to English.",
30
+ "pre_prompt_prefix": "",
31
+ "pre_prompt_suffix": "",
32
+ "seed": -1,
33
+ "tfs_z": 1,
34
+ "typical_p": 1,
35
+ "repeat_last_n": 64,
36
+ "frequency_penalty": 0,
37
+ "presence_penalty": 0,
38
+ "n_keep": 0,
39
+ "logit_bias": {},
40
+ "mirostat": 0,
41
+ "mirostat_tau": 5,
42
+ "mirostat_eta": 0.1,
43
+ "memory_f16": true,
44
+ "multiline_input": false,
45
+ "penalize_nl": true
46
+ }
47
+ }