aisuko commited on
Commit
e493fd2
1 Parent(s): db1342b

Add gpt2 xl gguf

Browse files

Signed-off-by: Aisuko <urakiny@gmail.com>

.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ *.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,56 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+
6
+
7
+ # The result of 1.5B GPT2
8
+
9
+ ```markdown
10
+
11
+ system_info: n_threads = 4 / 8 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
12
+ main: interactive mode on.
13
+ Reverse prompt: 'User:'
14
+ sampling:
15
+ repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
16
+ top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
17
+ mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
18
+ sampling order:
19
+ CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
20
+ generate: n_ctx = 1024, n_batch = 2048, n_predict = 256, n_keep = 0
21
+
22
+
23
+ == Running in interactive mode. ==
24
+ - Press Ctrl+C to interject at any time.
25
+ - Press Return to return control to the AI.
26
+ - To return control without starting a new line, end your input with '/'.
27
+ - If you want to submit another line, end your input with '\'.
28
+
29
+ Transcript of a dialog, where the User interacts with an Assistant named Bob. Bob is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.
30
+
31
+ User: Hello, Bob.
32
+ Bob: Hello. How may I help you today?
33
+ User: Please tell me the largest city in Europe.
34
+ Bob: Sure. The largest city in Europe is Moscow, the capital of Russia.
35
+ User:What is the largest city in Australia?
36
+
37
+ Bob: The largest city in Australia is Melbourne, the capital of Victoria.
38
+
39
+ User:What is the largest city in US
40
+
41
+ Bob: The largest city in US is Los Angeles, the capital of California.
42
+
43
+ User:thanks
44
+
45
+ Bob:Thanks for calling.
46
+
47
+ Bob is not a robot, and may be a human being who is not a robot. Bob is an Assistant that is helpful, kind, honest, good at writing and never fails to answer the User's requests.
48
+
49
+ User:
50
+
51
+ llama_print_timings: load time = 227.51 ms
52
+ llama_print_timings: sample time = 3.31 ms / 97 runs ( 0.03 ms per token, 29269.76 tokens per second)
53
+ llama_print_timings: prompt eval time = 29632.23 ms / 116 tokens ( 255.45 ms per token, 3.91 tokens per second)
54
+ llama_print_timings: eval time = 4239.84 ms / 94 runs ( 45.10 ms per token, 22.17 tokens per second)
55
+ llama_print_timings: total time = 76118.37 ms / 210 tokens
56
+ ```
gpt2-xl-Q4_K_M-v2.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2ef2b7c4b9d9d1c91e7828d6e6340b949c0b857948daf167d47eaebc72a293
3
+ size 1191798912
gpt2-xl-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2ef2b7c4b9d9d1c91e7828d6e6340b949c0b857948daf167d47eaebc72a293
3
+ size 1191798912
gpt2-xl-fp16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d744f0aed20ec3c2b8c3bd3958f68606fcd96a35ad8414e0b698e2c984fe11
3
+ size 3283124064