Upload LlamaForCausalLM
Browse files- config.json +5 -10
- generation_config.json +1 -0
- pytorch_model-00001-of-00014.bin +2 -2
- pytorch_model-00002-of-00014.bin +1 -1
- pytorch_model-00003-of-00014.bin +1 -1
- pytorch_model-00004-of-00014.bin +1 -1
- pytorch_model-00005-of-00014.bin +1 -1
- pytorch_model-00006-of-00014.bin +1 -1
- pytorch_model-00007-of-00014.bin +1 -1
- pytorch_model-00008-of-00014.bin +1 -1
- pytorch_model-00009-of-00014.bin +1 -1
- pytorch_model-00010-of-00014.bin +1 -1
- pytorch_model-00011-of-00014.bin +1 -1
- pytorch_model-00012-of-00014.bin +1 -1
- pytorch_model-00013-of-00014.bin +1 -1
- pytorch_model-00014-of-00014.bin +2 -2
- pytorch_model.bin.index.json +1 -1
config.json
CHANGED
|
@@ -1,32 +1,27 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "TinyPixel/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
-
"auto_map": {
|
| 7 |
-
"AutoConfig": "TheBloke/CodeLlama-7B-fp16--configuration_llama.LlamaConfig",
|
| 8 |
-
"AutoModel": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaModel",
|
| 9 |
-
"AutoModelForCausalLM": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForCausalLM",
|
| 10 |
-
"AutoModelForSequenceClassification": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForSequenceClassification"
|
| 11 |
-
},
|
| 12 |
"bos_token_id": 1,
|
| 13 |
"eos_token_id": 2,
|
| 14 |
"hidden_act": "silu",
|
| 15 |
"hidden_size": 4096,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 11008,
|
| 18 |
-
"max_position_embeddings":
|
| 19 |
"model_type": "llama",
|
| 20 |
"num_attention_heads": 32,
|
| 21 |
"num_hidden_layers": 32,
|
| 22 |
"num_key_value_heads": 32,
|
|
|
|
| 23 |
"pretraining_tp": 1,
|
| 24 |
"rms_norm_eps": 1e-05,
|
| 25 |
"rope_scaling": null,
|
| 26 |
-
"rope_theta":
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
"torch_dtype": "bfloat16",
|
| 29 |
"transformers_version": "4.34.0.dev0",
|
| 30 |
"use_cache": true,
|
| 31 |
-
"vocab_size":
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"bos_token_id": 1,
|
| 7 |
"eos_token_id": 2,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 4096,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
"model_type": "llama",
|
| 14 |
"num_attention_heads": 32,
|
| 15 |
"num_hidden_layers": 32,
|
| 16 |
"num_key_value_heads": 32,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
"pretraining_tp": 1,
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
"transformers_version": "4.34.0.dev0",
|
| 25 |
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,6 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
|
|
|
| 5 |
"transformers_version": "4.34.0.dev0"
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.34.0.dev0"
|
| 7 |
}
|
pytorch_model-00001-of-00014.bin
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 sha256:13dca03043e2204329753053c8d85e9bc232d340c4a80566a76b193ca260e846
|
| 3 |
+
size 981489327
|
pytorch_model-00002-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966844269
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26e4072c445f0d7bcdb66eeae88ae74e8550a18c7f040873781e27a288bd4d0e
|
| 3 |
size 966844269
|
pytorch_model-00003-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966827273
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc453a7bde53abb560d627117f11e3bd933acd79f9bd87986e3c53285ae136f
|
| 3 |
size 966827273
|
pytorch_model-00004-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 989912603
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65a78480f23fbacf5607dbf303ed3c52af899a0d4d47f12e1dc362e7bed35036
|
| 3 |
size 989912603
|
pytorch_model-00005-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 943758939
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d485f1350eb0b87b5aff649625d095d7e9e8bc584f851eb7889ecf1f9bfd8ac4
|
| 3 |
size 943758939
|
pytorch_model-00006-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 989895607
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee0078a1b12120eb0c95c44792dfbbbbab333bcc78b2de0382ce9488b49e1aee
|
| 3 |
size 989895607
|
pytorch_model-00007-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966844269
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec72061d9c7a3a9063e45bbe6115841f1fa596638443d7e6edab9a6d82019fcf
|
| 3 |
size 966844269
|
pytorch_model-00008-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966827273
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f8a31054f3a98f36bae88dcc15b8b65ec95987e9a5da6d98d8dc2497d61a945
|
| 3 |
size 966827273
|
pytorch_model-00009-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 989912667
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e5a0f05b1797b76d61edc3ad7b133603b56a2be647b2267cafbfde69e8022c
|
| 3 |
size 989912667
|
pytorch_model-00010-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 943758939
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c74df24f96e90ee7faa3783bba447c98cc8a2a3b1ff5289b94879274e4e17c1b
|
| 3 |
size 943758939
|
pytorch_model-00011-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 989895607
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baa7bb3d343c41be9f630e936b1da919c77681251bd2ec44f25febe8fad333d5
|
| 3 |
size 989895607
|
pytorch_model-00012-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966844269
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb3f88238a2405549949fc58f5bffc9f9af524d8dcf7d848b459769384b0a8dd
|
| 3 |
size 966844269
|
pytorch_model-00013-of-00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966827273
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beed225f18d508e6807fffe35dca5bc85fab88fdb18ec094040b0ed6b73125a3
|
| 3 |
size 966827273
|
pytorch_model-00014-of-00014.bin
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:b7fccbb47e99f74efbc81bcde41ae8d8442066bb6416278bce9dcd22a2854549
|
| 3 |
+
size 847295773
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 13476831232
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
|