Commit
•
0b03487
1
Parent(s):
b256ade
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
llama-2-tiny-random - GGUF
|
11 |
+
- Model creator: https://huggingface.co/yujiepan/
|
12 |
+
- Original model: https://huggingface.co/yujiepan/llama-2-tiny-random/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [llama-2-tiny-random.Q2_K.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q2_K.gguf) | Q2_K | 0.0GB |
|
18 |
+
| [llama-2-tiny-random.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.IQ3_XS.gguf) | IQ3_XS | 0.0GB |
|
19 |
+
| [llama-2-tiny-random.IQ3_S.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.IQ3_S.gguf) | IQ3_S | 0.0GB |
|
20 |
+
| [llama-2-tiny-random.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q3_K_S.gguf) | Q3_K_S | 0.0GB |
|
21 |
+
| [llama-2-tiny-random.IQ3_M.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.IQ3_M.gguf) | IQ3_M | 0.0GB |
|
22 |
+
| [llama-2-tiny-random.Q3_K.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q3_K.gguf) | Q3_K | 0.0GB |
|
23 |
+
| [llama-2-tiny-random.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q3_K_M.gguf) | Q3_K_M | 0.0GB |
|
24 |
+
| [llama-2-tiny-random.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q3_K_L.gguf) | Q3_K_L | 0.0GB |
|
25 |
+
| [llama-2-tiny-random.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.IQ4_XS.gguf) | IQ4_XS | 0.0GB |
|
26 |
+
| [llama-2-tiny-random.Q4_0.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q4_0.gguf) | Q4_0 | 0.0GB |
|
27 |
+
| [llama-2-tiny-random.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.IQ4_NL.gguf) | IQ4_NL | 0.0GB |
|
28 |
+
| [llama-2-tiny-random.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q4_K_S.gguf) | Q4_K_S | 0.0GB |
|
29 |
+
| [llama-2-tiny-random.Q4_K.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q4_K.gguf) | Q4_K | 0.0GB |
|
30 |
+
| [llama-2-tiny-random.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q4_K_M.gguf) | Q4_K_M | 0.0GB |
|
31 |
+
| [llama-2-tiny-random.Q4_1.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q4_1.gguf) | Q4_1 | 0.0GB |
|
32 |
+
| [llama-2-tiny-random.Q5_0.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q5_0.gguf) | Q5_0 | 0.0GB |
|
33 |
+
| [llama-2-tiny-random.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q5_K_S.gguf) | Q5_K_S | 0.0GB |
|
34 |
+
| [llama-2-tiny-random.Q5_K.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q5_K.gguf) | Q5_K | 0.0GB |
|
35 |
+
| [llama-2-tiny-random.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q5_K_M.gguf) | Q5_K_M | 0.0GB |
|
36 |
+
| [llama-2-tiny-random.Q5_1.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q5_1.gguf) | Q5_1 | 0.0GB |
|
37 |
+
| [llama-2-tiny-random.Q6_K.gguf](https://huggingface.co/RichardErkhov/yujiepan_-_llama-2-tiny-random-gguf/blob/main/llama-2-tiny-random.Q6_K.gguf) | Q6_K | 0.0GB |
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
Original model description:
|
43 |
+
---
|
44 |
+
library_name: transformers
|
45 |
+
pipeline_tag: text-generation
|
46 |
+
inference: true
|
47 |
+
widget:
|
48 |
+
- text: Hello!
|
49 |
+
example_title: Hello world
|
50 |
+
group: Python
|
51 |
+
---
|
52 |
+
|
53 |
+
# yujiepan/llama-2-tiny-random
|
54 |
+
|
55 |
+
This model is **randomly initialized**, using the config from [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/yujiepan/llama-2-tiny-random/blob/main/config.json) but with the following modifications:
|
56 |
+
|
57 |
+
```json
|
58 |
+
{
|
59 |
+
"hidden_size": 8,
|
60 |
+
"intermediate_size": 32,
|
61 |
+
"num_attention_heads": 2,
|
62 |
+
"num_hidden_layers": 1,
|
63 |
+
"num_key_value_heads": 2,
|
64 |
+
}
|
65 |
+
|
66 |
+
```
|
67 |
+
|