deepseek-coder-6.7b-base weights
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- mlc-chat-config.json +81 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_100.bin +3 -0
- params_shard_101.bin +3 -0
- params_shard_102.bin +3 -0
- params_shard_103.bin +3 -0
- params_shard_104.bin +3 -0
- params_shard_105.bin +3 -0
- params_shard_106.bin +3 -0
- params_shard_107.bin +3 -0
- params_shard_108.bin +3 -0
- params_shard_109.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_110.bin +3 -0
- params_shard_111.bin +3 -0
- params_shard_112.bin +3 -0
- params_shard_113.bin +3 -0
- params_shard_114.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
mlc-chat-config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "llama",
|
4 |
+
"quantization": "q4f16_1",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 4096,
|
7 |
+
"intermediate_size": 11008,
|
8 |
+
"num_attention_heads": 32,
|
9 |
+
"num_hidden_layers": 32,
|
10 |
+
"rms_norm_eps": 1e-06,
|
11 |
+
"vocab_size": 32256,
|
12 |
+
"tie_word_embeddings": false,
|
13 |
+
"position_embedding_base": 100000,
|
14 |
+
"rope_scaling": null,
|
15 |
+
"context_window_size": 16384,
|
16 |
+
"prefill_chunk_size": 8192,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"head_dim": 128,
|
19 |
+
"tensor_parallel_shards": 1,
|
20 |
+
"pipeline_parallel_stages": 1,
|
21 |
+
"max_batch_size": 128,
|
22 |
+
"disaggregation": false
|
23 |
+
},
|
24 |
+
"vocab_size": 32256,
|
25 |
+
"context_window_size": 16384,
|
26 |
+
"sliding_window_size": -1,
|
27 |
+
"prefill_chunk_size": 8192,
|
28 |
+
"attention_sink_size": -1,
|
29 |
+
"tensor_parallel_shards": 1,
|
30 |
+
"pipeline_parallel_stages": 1,
|
31 |
+
"temperature": 1.0,
|
32 |
+
"presence_penalty": 0.0,
|
33 |
+
"frequency_penalty": 0.0,
|
34 |
+
"repetition_penalty": 1.0,
|
35 |
+
"top_p": 1.0,
|
36 |
+
"tokenizer_files": [
|
37 |
+
"tokenizer.json",
|
38 |
+
"tokenizer_config.json"
|
39 |
+
],
|
40 |
+
"tokenizer_info": {
|
41 |
+
"token_postproc_method": "byte_level",
|
42 |
+
"prepend_space_in_encode": false,
|
43 |
+
"strip_space_in_decode": false
|
44 |
+
},
|
45 |
+
"conv_template": {
|
46 |
+
"name": "deepseek",
|
47 |
+
"system_template": "{system_message}",
|
48 |
+
"system_message": "",
|
49 |
+
"system_prefix_token_ids": [
|
50 |
+
100000
|
51 |
+
],
|
52 |
+
"add_role_after_system_message": true,
|
53 |
+
"roles": {
|
54 |
+
"user": "User",
|
55 |
+
"assistant": "Assistant"
|
56 |
+
},
|
57 |
+
"role_templates": {
|
58 |
+
"user": "{user_message}",
|
59 |
+
"assistant": "{assistant_message}",
|
60 |
+
"tool": "{tool_message}"
|
61 |
+
},
|
62 |
+
"messages": [],
|
63 |
+
"seps": [
|
64 |
+
"\n\n",
|
65 |
+
"<\uff5cend\u2581of\u2581sentence\uff5c>"
|
66 |
+
],
|
67 |
+
"role_content_sep": ": ",
|
68 |
+
"role_empty_sep": ":",
|
69 |
+
"stop_str": [
|
70 |
+
"<\uff5cend\u2581of\u2581sentence\uff5c>"
|
71 |
+
],
|
72 |
+
"stop_token_ids": [
|
73 |
+
100001
|
74 |
+
],
|
75 |
+
"function_string": "",
|
76 |
+
"use_function_calling": false
|
77 |
+
},
|
78 |
+
"pad_token_id": 0,
|
79 |
+
"bos_token_id": 32013,
|
80 |
+
"eos_token_id": 32014
|
81 |
+
}
|
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 sha256:267251dfffd97dac0b4a59fa5209b3fd9c7643b2d5b22168e17e4703030fa876
|
3 |
+
size 66060288
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:809620966904bd00cb78eab47615a9855299e35a0870691d4fb20902338c9a89
|
3 |
+
size 30810112
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9f5bdf00c4d3086753554859446380441d4cad34ee15c659e24d9a7ea8bcde5
|
3 |
+
size 25165824
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60f32616a3c617ad30535a83daa1b0c8b7d74e42637ba28382819432eb4d36e4
|
3 |
+
size 22544384
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6465950085fe80527d41ee1693f5fa905e88a63122a3bdab8f3872ecb32a65e8
|
3 |
+
size 45088768
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86780de99748a379f6f7d5819a9f71f462a4f8eb62a4edaf32911eca1c475f39
|
3 |
+
size 25165824
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41e81c9cffafaf27a68575e008ca4bf552c41f4a6fa16871554f67acb2b55e64
|
3 |
+
size 32661504
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3681b927ed6433086bf75aa99b33f02293b1783df85a41bfe6e39489b39be9e
|
3 |
+
size 31989760
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b2582c285bac556801d310a249b56701595d6c89de0aa5abd16bacd371b087c
|
3 |
+
size 45088768
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b94d4d93b167aaaa1a1acc6da6b5f99901d1287bacef2b937ec74058825c4d52
|
3 |
+
size 25165824
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6921a237955c4bf7fdf91d9a2818b27a246c0a64ffc42f23225f3d9f509f713a
|
3 |
+
size 22544384
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:797261e7e5f876f9c07b80f88c563874c5a4f6c25c2eea393bdfb3694994e3ca
|
3 |
+
size 45088768
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7984795f5a64c3efb81fa7ae333bb26d6f15e566d16652abb56160e34070e3e4
|
3 |
+
size 25165824
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5be9cccf95981230a0ee534a6f2b66bf5085c3b517fd71165c54cd0f911daca
|
3 |
+
size 22544384
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ddf4f8e15a5ebfa4b11fe77ddb1f8f5e2e573f036e153610edec2868316e4b
|
3 |
+
size 32661504
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03c7ec1ce3c6299118f7fffb1bca4216fffa1896756950b2abc04f2d1c67865d
|
3 |
+
size 31989760
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a94f2a6d7f3bbe34c8ea1694f7e95747622dd91479932fbec0c62d532c00b7c
|
3 |
+
size 45088768
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe5631fa27e2f0063b6ace01a534bd1554b5f8aaa4eaca3af5150cbb39bf77da
|
3 |
+
size 25165824
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ecce3772c32cf591d72842ddcb83570a9c9dbeb910f1d67aa1211da90cd88a8
|
3 |
+
size 21045248
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9592e69d57c3c07c995e84a8b2227e92b7c3b96061cad9d695d9324bdc0924e5
|
3 |
+
size 45088768
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:056a11528c1339c1b743c788911e28347300d7286d7a12a08c768953da40b6e4
|
3 |
+
size 25165824
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6f6ae950fdb45d37b384f5202a2ae905106324656b63adc861ab01ea49efff4
|
3 |
+
size 32661504
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f35834b216b13173b0ee3a8fc261c5cf85459b20241217982ee8164568b76604
|
3 |
+
size 31989760
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43913d0be272f2c83079f8304afc62d6693ed6d946e9b1eff978910bd189f791
|
3 |
+
size 45088768
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c973db2c09ca713bb22d6a98ebe1f8c5e91a4150699ec5afdb1589e62385ddf4
|
3 |
+
size 25165824
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abb0e69ebe93e36b88475f2e88ad3d1d32990a510be92adf9f8772a44ceeaaa9
|
3 |
+
size 22544384
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5673061c94bb79eddc9de26e770bcfc9fa1fdf77b7f66c670cd417bed1125369
|
3 |
+
size 45088768
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59d1f0e0373ee4387275bbc61dde2111b02b319e3ed9b38445c2700fef75bbc9
|
3 |
+
size 45088768
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afa2f87f63f66883ef17f171434d61466ce6b31ffc330e5237662b06b53ba5af
|
3 |
+
size 25165824
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbddfc659984d7114fdd7ba16dfb248832260a7700c5c906e23be382fe800787
|
3 |
+
size 32661504
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb4fd9500f3bf00347f317aa3548607a9d205ff14b723363d49830dbe3054eb
|
3 |
+
size 31989760
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13451c68ca53c81a03fff9a41569b21db19ba3bda0f757026a4d4a6e309b59cf
|
3 |
+
size 45088768
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2e0f4a5f71652ee9951c2989c3bcb1978061517d253267ffdd6c6085c261c0e
|
3 |
+
size 25165824
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21bde33495faaf512483204b8051b1a1c69fe19dac560a93a7c94f92adf94198
|
3 |
+
size 22544384
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3bc9dccafb1f5fdd96249197afec9f8e65efcada84fd20fe6a2bf80015615ad
|
3 |
+
size 45088768
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3a3eee0b6e86565a683f01f0e3584bcc915915316c5d7ca0143dbae2a39c5d7
|
3 |
+
size 25165824
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1344881b32c46b64aa2d28f2826facd19345f83468f3cb7100e1448199f479c8
|
3 |
+
size 32661504
|
params_shard_29.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d38798b44a174b7c2abb05cc852cb6e3b8582b0b3d3295d6ef304aab3bcab63
|
3 |
+
size 66060288
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac82abe283b450f0c469129ef86d81b9af3c480e847c8cb831838ee83e3ea12a
|
3 |
+
size 25165824
|
params_shard_30.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22417fb20b4c3cf116c3a189e6adf1256d1addba779293f664da91407fc84350
|
3 |
+
size 22544384
|
params_shard_31.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67fc64408411270deb702dd34f5d1b9054377c75b62b7da9604e264af11c97a
|
3 |
+
size 45088768
|
params_shard_32.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1b60fc28190cb23e426525443f36f1ba1c7d1261a5235da92d1b82d8d1827e
|
3 |
+
size 25165824
|
params_shard_33.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057132b7a4c5ee70723ce1984d6650e4a2f841f69fd4650f11168fa3c01aaa89
|
3 |
+
size 29319168
|
params_shard_34.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc789fd697eaa0dbf50f67f9f73fcf756d7fb623d3e075a2efe5f0eb617e1063
|
3 |
+
size 31989760
|
params_shard_35.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d1d3cfb41736cad48e17f19b1c72beb9624736a805991fca4edeecc4c3d0dbb
|
3 |
+
size 45088768
|
params_shard_36.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb778cc3beac58eab60566d04578e6b34cdd95cd00ea57954796cb637bf1ecdd
|
3 |
+
size 25165824
|
params_shard_37.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5093a050a61cc6c7db9e7e90ce07d113dead0116323e6c4c97e8135dedf5b7a
|
3 |
+
size 22544384
|
params_shard_38.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655750c7c618c9a7d3e0f5a878354f644907ca448f9bc8d2fd37f2cbfc1ccd1e
|
3 |
+
size 45088768
|