Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- all_results.json +8 -0
- config.json +31 -0
- generation_config.json +6 -0
- model-00001-of-00059.safetensors +3 -0
- model-00002-of-00059.safetensors +3 -0
- model-00003-of-00059.safetensors +3 -0
- model-00004-of-00059.safetensors +3 -0
- model-00005-of-00059.safetensors +3 -0
- model-00006-of-00059.safetensors +3 -0
- model-00007-of-00059.safetensors +3 -0
- model-00008-of-00059.safetensors +3 -0
- model-00009-of-00059.safetensors +3 -0
- model-00010-of-00059.safetensors +3 -0
- model-00011-of-00059.safetensors +3 -0
- model-00012-of-00059.safetensors +3 -0
- model-00013-of-00059.safetensors +3 -0
- model-00014-of-00059.safetensors +3 -0
- model-00015-of-00059.safetensors +3 -0
- model-00016-of-00059.safetensors +3 -0
- model-00017-of-00059.safetensors +3 -0
- model-00018-of-00059.safetensors +3 -0
- model-00019-of-00059.safetensors +3 -0
- model-00020-of-00059.safetensors +3 -0
- model-00021-of-00059.safetensors +3 -0
- model-00022-of-00059.safetensors +3 -0
- model-00023-of-00059.safetensors +3 -0
- model-00024-of-00059.safetensors +3 -0
- model-00025-of-00059.safetensors +3 -0
- model-00026-of-00059.safetensors +3 -0
- model-00027-of-00059.safetensors +3 -0
- model-00028-of-00059.safetensors +3 -0
- model-00029-of-00059.safetensors +3 -0
- model-00030-of-00059.safetensors +3 -0
- model-00031-of-00059.safetensors +3 -0
- model-00032-of-00059.safetensors +3 -0
- model-00033-of-00059.safetensors +3 -0
- model-00034-of-00059.safetensors +3 -0
- model-00035-of-00059.safetensors +3 -0
- model-00036-of-00059.safetensors +3 -0
- model-00037-of-00059.safetensors +3 -0
- model-00038-of-00059.safetensors +3 -0
- model-00039-of-00059.safetensors +3 -0
- model-00040-of-00059.safetensors +3 -0
- model-00041-of-00059.safetensors +3 -0
- model-00042-of-00059.safetensors +3 -0
- model-00043-of-00059.safetensors +3 -0
- model-00044-of-00059.safetensors +3 -0
- model-00045-of-00059.safetensors +3 -0
- model-00046-of-00059.safetensors +3 -0
- model-00047-of-00059.safetensors +3 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.7717660098635039,
|
4 |
+
"train_runtime": 39910.8187,
|
5 |
+
"train_samples": 11530,
|
6 |
+
"train_samples_per_second": 0.867,
|
7 |
+
"train_steps_per_second": 0.027
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistral-community/Mixtral-8x22B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.39.3",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
+
}
|
model-00001-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d25690e0859b1a473de27cffdb8f539ffdb44aa7ddb1aecab5b392bed0cc86f5
|
3 |
+
size 4998663696
|
model-00002-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22a90635568a06a3c7474326109b4443303472f049b37d4f70cd33ca08639f15
|
3 |
+
size 4806799120
|
model-00003-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee1c831ba019ddc51c70b0c5307b5f29dd3bfb3b9be43b89bf6db6c0a3a02db6
|
3 |
+
size 4806799120
|
model-00004-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a61a1730f2e2f4c6f76e55e7838847bc132e875ad9e9c7bc54bb01dee815542
|
3 |
+
size 4806799120
|
model-00005-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41311eae67783ae7814002988068034e0fd39f695e6dcb175a9151697e84d005
|
3 |
+
size 4806799120
|
model-00006-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab44c85d4d3a6e47dde43b9bb5439345e1dfa04701692eebaaa13747bd52e94
|
3 |
+
size 4806799120
|
model-00007-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c81bf0cac83fbfdc72400a0c8ce2a50218805e052d76255ba4aa4c65b7aa8e2c
|
3 |
+
size 4806799120
|
model-00008-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a4893964f0ad9c415a310cf3c9baa79502bbc854619e9748c8532835052534
|
3 |
+
size 4806799120
|
model-00009-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:815c4e761a01e472469cca05f8b027050cf1f71604e45cb09245ebae92c5bb33
|
3 |
+
size 4806799120
|
model-00010-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230c5e178da7880b1bd172ed219f726c65650fe22a22c6e8dae6b23376b25382
|
3 |
+
size 4806799120
|
model-00011-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:973cf1da92ec6eea165eca6e24b6a7d8d7fa8dd30668ab6b6fc6ab69fcbd0d7d
|
3 |
+
size 4806799136
|
model-00012-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c849a2ca2baf632158b944998a1819425a7d83edf4a261901597f4507932f8c3
|
3 |
+
size 4806799152
|
model-00013-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb2b9df0a9fbcad6f7432d00482ec93bbfc5d2706d00c806c6293540f0cee9e2
|
3 |
+
size 4806799152
|
model-00014-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58bfa1e5b23f11cbbf2fcd3a7c7c4153191659a6f3018a3131d5cc242ddc1e9e
|
3 |
+
size 4806799152
|
model-00015-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe128cee08e2a223d953e0e21b93ba64038e5956f2146e2435c572d191ec649
|
3 |
+
size 4806799152
|
model-00016-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbe495f703174a96a69b6fc7d55799e692e1ea631415641aca00266b569e5fe
|
3 |
+
size 4806799152
|
model-00017-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64ebb11c065fd7eecea8457ee1ab2ddc435cf012e4b8bc9c8ba978e288604b48
|
3 |
+
size 4806799152
|
model-00018-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c2930c14963ba0220d145db7e7445829cfcd2db1b6f2abe469250c38b021e31
|
3 |
+
size 4806799152
|
model-00019-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f4f31a3abdfd66051fbe0d6e108a7b6a94935b12aed42af64900a5ad3e133c6
|
3 |
+
size 4806799152
|
model-00020-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d32c70183a1bd1b259143a06e406c3395db8d37e2521c0913ed32573b1941439
|
3 |
+
size 4806799152
|
model-00021-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:385af61e256e910b2ea152d41ff0ed96fdfd0e29119ac36ee7ad49e9f823d018
|
3 |
+
size 4806799152
|
model-00022-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f317f4ef5af1c6f3fa623da7ed0c75d72f12999a2c2547b17c5ca662c90bfe71
|
3 |
+
size 4806799152
|
model-00023-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d36e9406cd7739bea800af09844082c051bc30e045dbbf8e5493cf3fd5c22862
|
3 |
+
size 4806799152
|
model-00024-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fb94161fb9fce2b6b227c863bad2173055b4fe905aaa954141dba8a3cf712fa
|
3 |
+
size 4932529864
|
model-00025-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a9469c8ccaf87bc4c8a5d63f14300ae5ce5ac04740fff77b03c56513dc37c41
|
3 |
+
size 4995542848
|
model-00026-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:996cf357c354321bd929cbc32836aa617fcba64e9ea77be392186ab8b14c3688
|
3 |
+
size 4995542848
|
model-00027-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:141889a0ccc7e0070f9f58e9a4260a94ffa6790a84aacba7735f408121d57121
|
3 |
+
size 4932628288
|
model-00028-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:063db91c9fc15972cbf65345d7aabb1954e9e62e15cfe84595d4626a665d2cbf
|
3 |
+
size 4806774344
|
model-00029-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b930bf6bce9f288170926eb76e6d6d0fc254902d2da844c855711dc296dfb8e
|
3 |
+
size 4806799144
|
model-00030-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30021d0f18e717e7ee6b0f0425041382fc92465efbf79a58ed5527ab5d5bc284
|
3 |
+
size 4806799144
|
model-00031-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4545dba161c7a8e526b12d8a741b27582ec5a12d8fe00d9f1fce05d178cd7a30
|
3 |
+
size 4806799144
|
model-00032-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:720f6441da369ef15febe37eefca09520abaa9b1d68f6c2ee40af4a4939ee65f
|
3 |
+
size 4806799144
|
model-00033-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aabe7b30623cb7a28fa5e290ed10d638eef14acfd444e7e6ebfc8ea3a5063f5c
|
3 |
+
size 4806799152
|
model-00034-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ca1c40399b00f358bd9d3bb3adac41a2a1d01e95b0e8f14892e0a06bf9fb05
|
3 |
+
size 4806799152
|
model-00035-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f29c7e312d2338c9a372abd381bd66505836409097a454c56b537ff7a68b5a6f
|
3 |
+
size 4806799152
|
model-00036-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:085a17b3fb86366ac107cbe17753fc68a2954ad197cdc133029e0f15e9bda4e2
|
3 |
+
size 4806799152
|
model-00037-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06618627f896d7dd24a456d249cdc60b32f1bf53a54eb55971c3934ab95b481a
|
3 |
+
size 4806799152
|
model-00038-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c98b31eda6c55aea120f1775625dd5956cb2cb354bb5bcb76b076549d7eb91f1
|
3 |
+
size 4806799152
|
model-00039-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86def800eb2c584ffebcb0aea2409082bf7f09d9d70b87d1332ce54923145d3e
|
3 |
+
size 4806799152
|
model-00040-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:148d2d58ce0405b512b101d16745df7936a5eaf0561d0deb2fcf560faa6f8ea5
|
3 |
+
size 4806799152
|
model-00041-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f88004698417f5225f23c669b6b89a83830038944a91095f9082ea98dd22d0f8
|
3 |
+
size 4806799152
|
model-00042-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42ad47f69e5ce327eb3b98b6a08f7d7dfcc7c6c4d31b80f2edb06d5fb7f1f96f
|
3 |
+
size 4806799152
|
model-00043-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff5e57744b74dadbd03b115c605e2d3c3ce968231ce9ed7361f242542a8ec86
|
3 |
+
size 4806799152
|
model-00044-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f949578301d74f880b0e3ec8522d579c28d15574d3dda152361ba97ff29478e2
|
3 |
+
size 4806799152
|
model-00045-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32571e8f1e729d6fa175a3ec659ace85e1f17554820ac6395b86eefd30dda1cb
|
3 |
+
size 4806799152
|
model-00046-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb99f35772db00b765b4dedafa7ce6649fe3ad9e2c2cb31937138a3bf1448b6b
|
3 |
+
size 4806799152
|
model-00047-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f17446cb0c021275a5a784a49e0a0ebaa33cf118f6c6ae2b11a47212d5f481f
|
3 |
+
size 4806799152
|