Commit
•
5b653bf
1
Parent(s):
4440744
(Trained with Unsloth)
Browse files- config.json +29 -2
- generation_config.json +1 -1
- pytorch_model-00001-of-00004.bin +1 -1
- pytorch_model-00002-of-00004.bin +1 -1
- pytorch_model-00003-of-00004.bin +1 -1
- pytorch_model-00004-of-00004.bin +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -1,3 +1,30 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 500000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.41.1",
|
27 |
+
"unsloth_version": "2024.5",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 128256
|
30 |
+
}
|
generation_config.json
CHANGED
@@ -5,5 +5,5 @@
|
|
5 |
"max_length": 4096,
|
6 |
"temperature": 0.6,
|
7 |
"top_p": 0.9,
|
8 |
-
"transformers_version": "4.41.
|
9 |
}
|
|
|
5 |
"max_length": 4096,
|
6 |
"temperature": 0.6,
|
7 |
"top_p": 0.9,
|
8 |
+
"transformers_version": "4.41.1"
|
9 |
}
|
pytorch_model-00001-of-00004.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976718466
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:616f35e4cc92ab9d1aa0ef6078caf72bd1f4be3d8598bbecf127b0452e340b7e
|
3 |
size 4976718466
|
pytorch_model-00002-of-00004.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999827206
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd3ed38a898f041626ee2450a5faa095b3126fcfee79a78e9c0d3ff6b4712a81
|
3 |
size 4999827206
|
pytorch_model-00003-of-00004.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915939082
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f9b92cce5d1c306c3467da7ba73cc7e236929cd2d7833fe24ab2ae64b457c37
|
3 |
size 4915939082
|
pytorch_model-00004-of-00004.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168140873
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a669e1e54267939ccd443f0ec87ee17393e5021cf8af7e0820a0ca1513d52630
|
3 |
size 1168140873
|
tokenizer_config.json
CHANGED
@@ -2067,6 +2067,6 @@
|
|
2067 |
],
|
2068 |
"model_max_length": 8192,
|
2069 |
"pad_token": "[PAD]",
|
2070 |
-
"padding_side": "
|
2071 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2072 |
}
|
|
|
2067 |
],
|
2068 |
"model_max_length": 8192,
|
2069 |
"pad_token": "[PAD]",
|
2070 |
+
"padding_side": "left",
|
2071 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2072 |
}
|