Step 4000 alpha checkpoint.
Browse files- config.json +27 -0
- generation_config.json +8 -0
- ggml-model-f16.bin +3 -0
- ggml-model-q4_0.bin +3 -0
- ggml-model-q4_1.bin +3 -0
- ggml-model-q5_0.bin +3 -0
- ggml-model-q5_1.bin +3 -0
- ggml-model-q8_0.bin +3 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/finetune-data/models/CarperAI/pythia-2.8b-deduped-4k",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"gradient_checkpointing": true,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 2560,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 10240,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "gpt_neox",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"rotary_emb_base": 10000,
|
20 |
+
"rotary_pct": 0.25,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.27.2",
|
24 |
+
"use_cache": false,
|
25 |
+
"use_parallel_residual": true,
|
26 |
+
"vocab_size": 50277
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.27.2",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
ggml-model-f16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49ca5dadec79a5d52bc9f54dbf186f48786ff5a1f0050a1c8e7908b27e457f20
|
3 |
+
size 5552819827
|
ggml-model-q4_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b13e612b5dd02bf09e89cc79e7e197b5d03892a210f244b0fa277dfdd8f8d99
|
3 |
+
size 1738568947
|
ggml-model-q4_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07b48c139443f3d23e92c8ebc7630ab4a3951d6b0b9587a53f8da5acb8dab861
|
3 |
+
size 2085319027
|
ggml-model-q5_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23d7918761eba3216777cfefebbcbb99a9fc0e3d8d9f697e4d293f4f23b1c39f
|
3 |
+
size 1911943987
|
ggml-model-q5_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae673e569a06167842f49bb69f3d78ddb5049242a7b0eabeb542b80f1f133f48
|
3 |
+
size 2085319027
|
ggml-model-q8_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bca4bd5919552b09d54d17c32e814d534567c2026005a7e304ccb6e2b74599e4
|
3 |
+
size 3125569267
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e648fdd38d66b716b192158ae5f267fd64550fbe8226c2c46788a75994503a9f
|
3 |
+
size 6087170877
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|