Muhammadreza
commited on
Commit
•
8ddfce4
1
Parent(s):
22ef1d1
Upload MistralForCausalLM
Browse files- config.json +54 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Nuclues/Nucleus-1B-Pretrained",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 4,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"quantization_config": {
|
19 |
+
"batch_size": 1,
|
20 |
+
"bits": 4,
|
21 |
+
"block_name_to_quantize": null,
|
22 |
+
"cache_block_outputs": true,
|
23 |
+
"damp_percent": 0.1,
|
24 |
+
"dataset": [
|
25 |
+
"This is just a test dataset.",
|
26 |
+
"It will mess with the accuracy, but doesn't matter",
|
27 |
+
"Okay, Lily is awesome",
|
28 |
+
"And now, you have your mother's eyes potter"
|
29 |
+
],
|
30 |
+
"desc_act": false,
|
31 |
+
"exllama_config": {
|
32 |
+
"version": 1
|
33 |
+
},
|
34 |
+
"group_size": 128,
|
35 |
+
"max_input_length": null,
|
36 |
+
"model_seqlen": null,
|
37 |
+
"module_name_preceding_first_block": null,
|
38 |
+
"pad_token_id": null,
|
39 |
+
"quant_method": "gptq",
|
40 |
+
"sym": true,
|
41 |
+
"tokenizer": null,
|
42 |
+
"true_sequential": true,
|
43 |
+
"use_cuda_fp16": false,
|
44 |
+
"use_exllama": true
|
45 |
+
},
|
46 |
+
"rms_norm_eps": 1e-05,
|
47 |
+
"rope_theta": 10000.0,
|
48 |
+
"sliding_window": 4096,
|
49 |
+
"tie_word_embeddings": false,
|
50 |
+
"torch_dtype": "float16",
|
51 |
+
"transformers_version": "4.36.2",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 32000
|
54 |
+
}
|
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": "4.36.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e7a2c5b78285c72f0b8bf0d1f14bb1dafafc6200e6aec078991f371a2be00b
|
3 |
+
size 978591824
|