RichardErkhov
commited on
Commit
•
7352a71
1
Parent(s):
34ed47c
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
gemma-7b-openhermes-v0.80 - GGUF
|
11 |
+
- Model creator: https://huggingface.co/lemon-mint/
|
12 |
+
- Original model: https://huggingface.co/lemon-mint/gemma-7b-openhermes-v0.80/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [gemma-7b-openhermes-v0.80.Q2_K.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q2_K.gguf) | Q2_K | 3.24GB |
|
18 |
+
| [gemma-7b-openhermes-v0.80.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.IQ3_XS.gguf) | IQ3_XS | 3.54GB |
|
19 |
+
| [gemma-7b-openhermes-v0.80.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.IQ3_S.gguf) | IQ3_S | 3.71GB |
|
20 |
+
| [gemma-7b-openhermes-v0.80.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q3_K_S.gguf) | Q3_K_S | 3.71GB |
|
21 |
+
| [gemma-7b-openhermes-v0.80.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.IQ3_M.gguf) | IQ3_M | 3.82GB |
|
22 |
+
| [gemma-7b-openhermes-v0.80.Q3_K.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q3_K.gguf) | Q3_K | 4.07GB |
|
23 |
+
| [gemma-7b-openhermes-v0.80.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q3_K_M.gguf) | Q3_K_M | 4.07GB |
|
24 |
+
| [gemma-7b-openhermes-v0.80.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q3_K_L.gguf) | Q3_K_L | 4.39GB |
|
25 |
+
| [gemma-7b-openhermes-v0.80.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.IQ4_XS.gguf) | IQ4_XS | 4.48GB |
|
26 |
+
| [gemma-7b-openhermes-v0.80.Q4_0.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q4_0.gguf) | Q4_0 | 4.67GB |
|
27 |
+
| [gemma-7b-openhermes-v0.80.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.IQ4_NL.gguf) | IQ4_NL | 4.69GB |
|
28 |
+
| [gemma-7b-openhermes-v0.80.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q4_K_S.gguf) | Q4_K_S | 4.7GB |
|
29 |
+
| [gemma-7b-openhermes-v0.80.Q4_K.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q4_K.gguf) | Q4_K | 4.96GB |
|
30 |
+
| [gemma-7b-openhermes-v0.80.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q4_K_M.gguf) | Q4_K_M | 4.96GB |
|
31 |
+
| [gemma-7b-openhermes-v0.80.Q4_1.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q4_1.gguf) | Q4_1 | 5.12GB |
|
32 |
+
| [gemma-7b-openhermes-v0.80.Q5_0.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q5_0.gguf) | Q5_0 | 5.57GB |
|
33 |
+
| [gemma-7b-openhermes-v0.80.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q5_K_S.gguf) | Q5_K_S | 5.57GB |
|
34 |
+
| [gemma-7b-openhermes-v0.80.Q5_K.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q5_K.gguf) | Q5_K | 5.72GB |
|
35 |
+
| [gemma-7b-openhermes-v0.80.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q5_K_M.gguf) | Q5_K_M | 5.72GB |
|
36 |
+
| [gemma-7b-openhermes-v0.80.Q5_1.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q5_1.gguf) | Q5_1 | 6.02GB |
|
37 |
+
| [gemma-7b-openhermes-v0.80.Q6_K.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q6_K.gguf) | Q6_K | 6.53GB |
|
38 |
+
| [gemma-7b-openhermes-v0.80.Q8_0.gguf](https://huggingface.co/RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf/blob/main/gemma-7b-openhermes-v0.80.Q8_0.gguf) | Q8_0 | 8.45GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
---
|
45 |
+
library_name: transformers
|
46 |
+
language:
|
47 |
+
- en
|
48 |
+
license: gemma
|
49 |
+
tags:
|
50 |
+
- gemma
|
51 |
+
- pytorch
|
52 |
+
- instruct
|
53 |
+
- finetune
|
54 |
+
base_model: google/gemma-1.1-7b-it
|
55 |
+
pipeline_tag: text-generation
|
56 |
+
datasets:
|
57 |
+
- teknium/OpenHermes-2.5
|
58 |
+
---
|
59 |
+
|
60 |
+
|
61 |
+
# Gemma 7B OpenHermes v0.80
|
62 |
+
|
63 |
+
- Eval Loss: `0.4544`
|
64 |
+
- Train Loss: `0.3129`
|
65 |
+
- lr: `5e-5`
|
66 |
+
- optimizer: adamw
|
67 |
+
- lr_scheduler_type: cosine
|
68 |
+
|
69 |
+
## Model Details
|
70 |
+
|
71 |
+
This is an instruction-following model finetuned from the Gemma 1.1 7B model. It was finetuned on the OpenHermes-2.5 dataset to improve its ability to engage in open-ended conversation and respond helpfully to user instructions and queries. The model can engage in dialogue, answer questions, and assist with a variety of tasks.
|
72 |
+
|
73 |
+
### Model Description
|
74 |
+
|
75 |
+
- **Developed by:** `lemon-mint`
|
76 |
+
- **Model type:** Gemma
|
77 |
+
- **Language(s) (NLP):** English
|
78 |
+
- **License:** [gemma-terms-of-use](https://ai.google.dev/gemma/terms)
|
79 |
+
- **Finetuned from model:** [google/gemma-1.1-7b-it](https://huggingface.co/google/gemma-1.1-7b-it)
|
80 |
+
|
81 |
+
# Limitations and Ethical Considerations
|
82 |
+
|
83 |
+
As Gemma 7B OpenHermes has been trained on extensive web data, biases present in the training data may be reflected in the model. Additionally, there is a possibility that it may generate sentences containing errors or incorrect information. Therefore, rather than blindly trusting the model's output, it is necessary to refer to it with caution.
|
84 |
+
|