Hugging Face's logo

junrushao
/
gpt_bigcode-santacoder-q3f16_1-MLC

Model card Files Community
junrushao commited on
Commit
c6ee1b1
·
1 Parent(s): 45d3dd0

Initial commit

Browse files
Files changed (24) hide show
  1. logs.txt +0 -0
  2. mlc-chat-config.json +38 -0
  3. ndarray-cache.json +0 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_10.bin +3 -0
  7. params_shard_11.bin +3 -0
  8. params_shard_12.bin +3 -0
  9. params_shard_13.bin +3 -0
  10. params_shard_14.bin +3 -0
  11. params_shard_15.bin +3 -0
  12. params_shard_16.bin +3 -0
  13. params_shard_17.bin +3 -0
  14. params_shard_18.bin +3 -0
  15. params_shard_2.bin +3 -0
  16. params_shard_3.bin +3 -0
  17. params_shard_4.bin +3 -0
  18. params_shard_5.bin +3 -0
  19. params_shard_6.bin +3 -0
  20. params_shard_7.bin +3 -0
  21. params_shard_8.bin +3 -0
  22. params_shard_9.bin +3 -0
  23. tokenizer.json +0 -0
  24. tokenizer_config.json +7 -0
logs.txt ADDED
The diff for this file is too large to render. See raw diff
 
mlc-chat-config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "gpt_bigcode",
3
+ "quantization": "q3f16_1",
4
+ "model_config": {
5
+ "n_embd": 2048,
6
+ "n_inner": 8192,
7
+ "n_head": 16,
8
+ "n_layer": 24,
9
+ "n_positions": 2048,
10
+ "layer_norm_epsilon": 1e-05,
11
+ "vocab_size": 49280,
12
+ "context_window_size": 2048,
13
+ "prefill_chunk_size": 2048,
14
+ "tensor_parallel_shards": 1
15
+ },
16
+ "vocab_size": 49280,
17
+ "context_window_size": 2048,
18
+ "sliding_window_size": -1,
19
+ "prefill_chunk_size": 2048,
20
+ "attention_sink_size": -1,
21
+ "tensor_parallel_shards": 1,
22
+ "max_batch_size": 80,
23
+ "mean_gen_len": 128,
24
+ "max_gen_len": 512,
25
+ "shift_fill_factor": 0.3,
26
+ "temperature": 0.7,
27
+ "repetition_penalty": 1.0,
28
+ "top_p": 0.95,
29
+ "conv_template": "LM",
30
+ "pad_token_id": 0,
31
+ "bos_token_id": 49152,
32
+ "eos_token_id": 49152,
33
+ "tokenizer_files": [
34
+ "tokenizer.json",
35
+ "tokenizer_config.json"
36
+ ],
37
+ "version": "0.1.0"
38
+ }
ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdec8ef59d5e15c630e9848213d37d55089fa17c674fbabca4b800cdb3c1ffd9
3
+ size 41000960
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015150f9f683940992333b6a0f67e0ab07499a1b13eeb4c7efe372ddd7b2e33c
3
+ size 30484480
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4e1b58ed644a79fbbd4cf31f33d4c42ea4eb3270acec55d436b32d955fd74c
3
+ size 27027968
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785fd661ad14ee78936cfbddfd99cb8a06238be105608a1134b63e5c43b06fdf
3
+ size 31003648
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957733a6e7557d5fca427aa728ffd2bde11a5c2fb681d150726f6805b543abd1
3
+ size 27027968
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931bb9cdb445ca8ebbc6ae7316f1ee00f85b90fe50f7eac3471815f095078b74
3
+ size 31003648
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f4b6d9777b4ca3146c9554129dc70a92cd352dd143380382422fc19c90eeef
3
+ size 27027968
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc290019df06b81944b2bf287ea1f8764a6344d4d1fcafd6cf72e0bde820c0b
3
+ size 31003648
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989685f2b1c6f4a3e7963ea44f4f3c0ec4ba34efbd31b4a7ca21c60694b8bd7e
3
+ size 27027968
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdec8ef59d5e15c630e9848213d37d55089fa17c674fbabca4b800cdb3c1ffd9
3
+ size 41000960
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36b99d9954e03366d9214e063a69fe126f94aa30db319b863dcf26be64d43e4
3
+ size 12694528
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2df0538cee0616e34c8aa3945540c7db85e9c04516ccbda1f8ca5768f0c4fe
3
+ size 27027968
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e24ec11b70c1707669f8d9a21a5dd9d8abf8fe13bcd13eae3e5000227421796
3
+ size 31003648
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb86f872fc8ea74b2618ff0f9938c5a1d253c0bbc38856ddb2bc16ffdfbb5ec7
3
+ size 27027968
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094843d63302da0ae08e67607d10c8749967c7462f574bb9b07ae51b48e12382
3
+ size 31003648
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a3aae4613b288e3bbd51a241124f654772ec1c22d8b2d2b69305b83531a95c
3
+ size 27027968
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d3057852d32456004088eb12109cb0ae7d79b1798a33f3a1dca4beceb2d751
3
+ size 31003648
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b2857ab8fc26f83daa5c5f890a59f7ba59747c5df73d90cbdca64e0c2d628c
3
+ size 27027968
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8cbc1f2a71fc06ae8758040727438cc45de27c5cca2baeb19f1bb87b17c35c
3
+ size 31003648
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "errors": "replace",
3
+ "tokenizer_class": "GPT2TokenizerFast",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048
7
+ }