2859057289238237110c14e24f6da0872277621881b8d6db4c95775174e5ebfb
Browse files- .gitattributes +10 -0
- checkpoint/pytorch_model.bin/p84.model.layers.9.self_attn.v_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p85.model.layers.9.self_attn.o_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight +2 -2
- checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight +2 -2
- checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight +2 -2
- checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +2 -2
- checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +2 -2
- checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +2 -2
- compiled/22c9e8c61931750704e4.neff +3 -0
- compiled/6e28cdc209d01cf80749.neff +3 -0
- compiled/79e2d4e60d54467c6d8c.neff +3 -0
- compiled/89ecf163d454a64c0c00.neff +3 -0
- compiled/a433e75bc0664453b177.neff +3 -0
- compiled/be670fb677a32755b5fc.neff +3 -0
- compiled/bed5751f3dea8390f0f6.neff +3 -0
- compiled/d4a2099a3da7ae458edf.neff +3 -0
- compiled/e2ed77001ff9f87f5f60.neff +3 -0
- compiled/e497ac4eb1b05d80f918.neff +3 -0
- config.json +6 -3
- generation_config.json +1 -1
.gitattributes
CHANGED
@@ -43,3 +43,13 @@ compiled/b59dca76c353105042b2.neff filter=lfs diff=lfs merge=lfs -text
|
|
43 |
compiled/d9a9b3aab1095d21dc94.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
compiled/e6af685a35c321de6779.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
compiled/ee57f53ab745d1cbe07e.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
compiled/d9a9b3aab1095d21dc94.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
compiled/e6af685a35c321de6779.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
compiled/ee57f53ab745d1cbe07e.neff filter=lfs diff=lfs merge=lfs -text
|
46 |
+
compiled/22c9e8c61931750704e4.neff filter=lfs diff=lfs merge=lfs -text
|
47 |
+
compiled/6e28cdc209d01cf80749.neff filter=lfs diff=lfs merge=lfs -text
|
48 |
+
compiled/79e2d4e60d54467c6d8c.neff filter=lfs diff=lfs merge=lfs -text
|
49 |
+
compiled/89ecf163d454a64c0c00.neff filter=lfs diff=lfs merge=lfs -text
|
50 |
+
compiled/a433e75bc0664453b177.neff filter=lfs diff=lfs merge=lfs -text
|
51 |
+
compiled/be670fb677a32755b5fc.neff filter=lfs diff=lfs merge=lfs -text
|
52 |
+
compiled/bed5751f3dea8390f0f6.neff filter=lfs diff=lfs merge=lfs -text
|
53 |
+
compiled/d4a2099a3da7ae458edf.neff filter=lfs diff=lfs merge=lfs -text
|
54 |
+
compiled/e2ed77001ff9f87f5f60.neff filter=lfs diff=lfs merge=lfs -text
|
55 |
+
compiled/e497ac4eb1b05d80f918.neff filter=lfs diff=lfs merge=lfs -text
|
checkpoint/pytorch_model.bin/p84.model.layers.9.self_attn.v_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff4feaa079a438738eb8bb236faaaccfea37483ca40de35693c9bbe8b8db3720
|
3 |
+
size 33555327
|
checkpoint/pytorch_model.bin/p85.model.layers.9.self_attn.o_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a9e96ba648d914ce77ed095d9706f2a33bcbd15ae5ca4eaa310894ca0c39f4e
|
3 |
+
size 33555327
|
checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f41fe1dc3514a5e45904e67134c82aa46301e25b0724787f8ed7a83c6be7440
|
3 |
+
size 90178422
|
checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a501b183fc535240cc500483c19261ebc0c2eae53d00ce44d8658ffdbfddb62
|
3 |
+
size 90178416
|
checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a78558ea1ac861500edc11b2e464d9e4232d2af76dc003665dc3c4056253a27a
|
3 |
+
size 90178422
|
checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ae3b121d3a97fa73da80c01577994fd364e16180d7a6bb02d8eb57b55448300
|
3 |
+
size 9084
|
checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc6c5a0477f3dfa4b5f15f923813181ec61a32c89310dd4a09726d447ae20a53
|
3 |
+
size 9108
|
checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40738baf98fa9fb2b3c5c3e4b9b1ea81efa1a745e9223f5eb22846625f1c269
|
3 |
+
size 9111
|
checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e1f83bd8f582d1dafe189cfbcb33c4af7e0a4a881b8dd5bba743034d21b75d
|
3 |
+
size 33555330
|
checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d318a67492fc958ee5e6705d2720df800b8b6cff8de6fadcca53fa27dd80e21d
|
3 |
+
size 33555330
|
checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f39f768edc454de8918a7e36cb2869f8606a4c668606d7540e2e5979ddffbaa
|
3 |
+
size 33555330
|
checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525b3ee20ab2c09d1182b9d7267c5bd315c7b3ba997fd6bea5115990398ea8b5
|
3 |
+
size 33555330
|
checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:342af5aea61446b7d940d89a402382dc85a053910c78fd5a75eec78aadad3f55
|
3 |
+
size 90178425
|
checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23cd6824ee97af97480470af661f5a87b812e81609a3c4ed45e45d1a961303d4
|
3 |
+
size 90178419
|
checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14bcfeead8bf5504a6c7e2615f60d9a7229837f842d3c999022a843562232688
|
3 |
+
size 90178425
|
checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:712531a293427af916005f4123df9dfa8c949d06a351f8909ebf4b26d4e3a1ef
|
3 |
+
size 9087
|
checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc29728ad949701d823889a0382cd6f123d3d5011a174f6386662a147af746a
|
3 |
+
size 9114
|
compiled/22c9e8c61931750704e4.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066ed7231ca921e398dfff0074d771c9ea6f2bab56c4611dc6a518f72e5537e8
|
3 |
+
size 8172544
|
compiled/6e28cdc209d01cf80749.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d90301ec5603a6b4df1ff4ab6dc9bc7e6c1b79253df9d584d95a537745319a7
|
3 |
+
size 8479744
|
compiled/79e2d4e60d54467c6d8c.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:594ddf2c73cfa55369791fa73f4820cded486fa7a2bdfcc0c5759a443ba0d25b
|
3 |
+
size 23624704
|
compiled/89ecf163d454a64c0c00.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fd7cf811ef927376a7b61eaa272c228ff8fc40747e828771bb6f06a1b4f709c
|
3 |
+
size 8909824
|
compiled/a433e75bc0664453b177.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9cebaa5e62de70404d075dc408b820fb992a5fef1a00ec4e7f2e2c43f186d86
|
3 |
+
size 7998464
|
compiled/be670fb677a32755b5fc.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8610b9bcc58d05574b551f08cd2c9a1d6ca50ccea996afbb38dc17a601260e78
|
3 |
+
size 7916544
|
compiled/bed5751f3dea8390f0f6.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:712fab2ce64acf0f9dae0b61fc8a09e595780ad5331475f68cb8bbc9afe77e55
|
3 |
+
size 12770304
|
compiled/d4a2099a3da7ae458edf.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f0035df9d84215a053b9acde2cf9063eae2fa936cd607d0425e71c63345ce4
|
3 |
+
size 9923584
|
compiled/e2ed77001ff9f87f5f60.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c8cea07f81026a7a9bfbbbc64eabe1f3522b0b0eaaf1ccd563411bf996fca6d
|
3 |
+
size 7875584
|
compiled/e497ac4eb1b05d80f918.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa8eec54ef2b0cb06f7d394a3a480099fa43c56c6f78a5933d4ca56a0ff6c07b
|
3 |
+
size 8551424
|
config.json
CHANGED
@@ -1,9 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "CodeLlama-7b-hf
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -15,8 +16,10 @@
|
|
15 |
"neuron": {
|
16 |
"auto_cast_type": "fp16",
|
17 |
"batch_size": 1,
|
|
|
|
|
18 |
"compiler_type": "neuronx-cc",
|
19 |
-
"compiler_version": "2.
|
20 |
"num_cores": 2,
|
21 |
"sequence_length": 2048,
|
22 |
"task": "text-generation"
|
@@ -30,7 +33,7 @@
|
|
30 |
"rope_theta": 1000000,
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
-
"transformers_version": "4.
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 32016
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "codellama/CodeLlama-7b-hf",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
|
|
16 |
"neuron": {
|
17 |
"auto_cast_type": "fp16",
|
18 |
"batch_size": 1,
|
19 |
+
"checkpoint_id": "codellama/CodeLlama-7b-hf",
|
20 |
+
"checkpoint_revision": "7f22f0a5f7991355a2c3867923359ec4ed0b58bf",
|
21 |
"compiler_type": "neuronx-cc",
|
22 |
+
"compiler_version": "2.12.68.0+4480452af",
|
23 |
"num_cores": 2,
|
24 |
"sequence_length": 2048,
|
25 |
"task": "text-generation"
|
|
|
33 |
"rope_theta": 1000000,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.36.2",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 32016
|
39 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
}
|