Text Generation
Transformers
GGUF
English
Inference Endpoints
leafspark commited on
Commit
0962e57
1 Parent(s): 427c469

Upload 2 files

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  ggml-wikichat-256x28-f32-4810.gguf 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
  ggml-wikichat-256x28-f32-4810.gguf filter=lfs diff=lfs merge=lfs -text
37
+ chk-wikichat-256x28-4810.gguf filter=lfs diff=lfs merge=lfs -text
chk-wikichat-256x28-4810.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02f4381ddc37aa4a88c349b2d5d801656d66dd8d19e403c0932c66dd27575ba
3
+ size 483790912
model_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "WikiGGML",
3
+ "load_params": {
4
+ "n_ctx": 2048,
5
+ "n_batch": 512,
6
+ "rope_freq_base": 0,
7
+ "rope_freq_scale": 0,
8
+ "n_gpu_layers": -1,
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
+ "no_kv_offload": false,
18
+ "num_experts_used": 0
19
+ },
20
+ "inference_params": {
21
+ "n_threads": 4,
22
+ "n_predict": -1,
23
+ "top_k": 40,
24
+ "min_p": 0.05,
25
+ "top_p": 0.95,
26
+ "temp": 0.8,
27
+ "repeat_penalty": 1.1,
28
+ "input_prefix": "User:",
29
+ "input_suffix": "\nA:",
30
+ "antiprompt": [
31
+ "### Instruction:",
32
+ "### User:\\n",
33
+ "User:\\n",
34
+ "User:"
35
+ ],
36
+ "pre_prompt": "",
37
+ "pre_prompt_suffix": "\\n",
38
+ "pre_prompt_prefix": "",
39
+ "seed": -1,
40
+ "tfs_z": 1,
41
+ "typical_p": 1,
42
+ "repeat_last_n": 64,
43
+ "frequency_penalty": 0,
44
+ "presence_penalty": 0,
45
+ "n_keep": 0,
46
+ "logit_bias": {},
47
+ "mirostat": 0,
48
+ "mirostat_tau": 5,
49
+ "mirostat_eta": 0.1,
50
+ "memory_f16": true,
51
+ "multiline_input": false,
52
+ "penalize_nl": true
53
+ }
54
+ }