Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- merge
|
6 |
+
base_model:
|
7 |
+
- 01-ai/Yi-1.5-34B-Chat
|
8 |
+
- 01-ai/Yi-1.5-34B
|
9 |
+
pipeline_tag: text-generation
|
10 |
+
---
|
11 |
+
|
12 |
+
#
|
13 |
+
<img src=https://huggingface.co/altomek/YiSM-34B-0rn/resolve/main/YiSM.png>
|
14 |
+
<a href="https://www.youtube.com/watch?v=a9dNpk9G5h0" title="P.T. Adamczyk - Never Looking Back | Cyberpunk 2077: Phantom Liberty (Original Score)" target="_blank">intro music...</a>
|
15 |
+
|
16 |
+
## YiSM-34B-0rn
|
17 |
+
|
18 |
+
This is Yi Self Merged. I wanted model that will follow most instuctions yet preserve its base model nature.
|
19 |
+
|
20 |
+
### Ingridients
|
21 |
+
|
22 |
+
- [Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat)
|
23 |
+
|
24 |
+
- [Yi-1.5-34B](https://huggingface.co/01-ai/Yi-1.5-34B-Chat/)
|
25 |
+
|
26 |
+
### Settings
|
27 |
+
|
28 |
+
I use max_seq_len 8K with alpha_value 2.65.
|
29 |
+
|
30 |
+
SillyTavern presets:
|
31 |
+
|
32 |
+
```json
|
33 |
+
{
|
34 |
+
"temp": 0.1,
|
35 |
+
"temperature_last": true,
|
36 |
+
"top_p": 1,
|
37 |
+
"top_k": 0,
|
38 |
+
"top_a": 0,
|
39 |
+
"tfs": 1,
|
40 |
+
"epsilon_cutoff": 0,
|
41 |
+
"eta_cutoff": 0,
|
42 |
+
"typical_p": 1,
|
43 |
+
"min_p": 0.8,
|
44 |
+
"rep_pen": 1.08,
|
45 |
+
"rep_pen_range": 0,
|
46 |
+
"no_repeat_ngram_size": 0,
|
47 |
+
"penalty_alpha": 0,
|
48 |
+
"num_beams": 1,
|
49 |
+
"length_penalty": 1,
|
50 |
+
"min_length": 0,
|
51 |
+
"encoder_rep_pen": 1,
|
52 |
+
"freq_pen": 0.01,
|
53 |
+
"presence_pen": 0,
|
54 |
+
"do_sample": true,
|
55 |
+
"early_stopping": false,
|
56 |
+
"add_bos_token": true,
|
57 |
+
"truncation_length": 2048,
|
58 |
+
"ban_eos_token": false,
|
59 |
+
"skip_special_tokens": true,
|
60 |
+
"streaming": true,
|
61 |
+
"mirostat_mode": 0,
|
62 |
+
"mirostat_tau": 5,
|
63 |
+
"mirostat_eta": 0.1,
|
64 |
+
"guidance_scale": 1,
|
65 |
+
"negative_prompt": "",
|
66 |
+
"grammar_string": "",
|
67 |
+
"banned_tokens": "",
|
68 |
+
"ignore_eos_token_aphrodite": false,
|
69 |
+
"spaces_between_special_tokens_aphrodite": true,
|
70 |
+
"sampler_order": [
|
71 |
+
6,
|
72 |
+
0,
|
73 |
+
1,
|
74 |
+
3,
|
75 |
+
4,
|
76 |
+
2,
|
77 |
+
5
|
78 |
+
],
|
79 |
+
"logit_bias": [],
|
80 |
+
"n": 1,
|
81 |
+
"rep_pen_size": 0,
|
82 |
+
"genamt": 2048,
|
83 |
+
"max_length": 8192
|
84 |
+
}
|
85 |
+
```
|
86 |
+
|
87 |
+
### Terms and Conditions of Use
|
88 |
+
|
89 |
+
The following table outlines the primary characteristics and intended uses of my YiSM-34B-0rn models:
|
90 |
+
|
91 |
+
| Model Type | Purpose | Target Users | Key Features |
|
92 |
+
| --- | --- | --- | --- |
|
93 |
+
| **Censored** | Suitable for general audiences and sensitive topics | Educational institutions, families, and individuals seeking age-appropriate content | Restricts explicit or mature material |
|
94 |
+
| **Neutral** (<u>**this one</u>) | Balances accessibility with openness | Universities, researchers, and curious minds | Encourages exploration and intellectual exchange |
|
95 |
+
| Uncensored | Ideal for adults and specialized fields | Professionals, experts, and advanced scholars | Offers unfiltered access to diverse viewpoints and knowledge |
|
96 |
+
|
97 |
+
Please remember that all YiSM-34B-0rn models operate under the apache-2.0 license, so familiarize yourself with its terms and conditions before employing their content.
|
98 |
+
|
99 |
+
|
100 |
+
### Quants
|
101 |
+
|
102 |
+
- [GGUF](https://huggingface.co/altomek/YiSM-34B-0rn-GGUF)
|
103 |
+
- [8bpw](https://huggingface.co/altomek/YiSM-34B-0rn-8bpw-EXL2)
|
104 |
+
- [measurements](https://huggingface.co/altomek/measurements/resolve/main/YiSM-34B-0rn_measurement.json) --> ExLlamav2 measurments
|