Downloads · 30 days
121
10% of all-time downloads
maldv_-_winter-garden-7b-beta-gguf
RichardErkhov/maldv_-_winter-garden-7b-beta-gguf
maldv_-_winter-garden-7b-beta-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.2K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 13, 2024
- Updated
- Sep 13, 2024
- SHA
- 9eead0fb
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
winter-garden-7b-beta - GGUF
- Model creator: https://huggingface.co/maldv/
- Original model: https://huggingface.co/maldv/winter-garden-7b-beta/
| Name | Quant method | Size |
|---|---|---|
| winter-garden-7b-beta.Q2_K.gguf | Q2_K | 2.53GB |
| winter-garden-7b-beta.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| winter-garden-7b-beta.IQ3_S.gguf | IQ3_S | 2.96GB |
| winter-garden-7b-beta.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| winter-garden-7b-beta.IQ3_M.gguf | IQ3_M | 3.06GB |
| winter-garden-7b-beta.Q3_K.gguf | Q3_K | 3.28GB |
| winter-garden-7b-beta.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| winter-garden-7b-beta.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| winter-garden-7b-beta.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| winter-garden-7b-beta.Q4_0.gguf | Q4_0 | 3.83GB |
| winter-garden-7b-beta.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| winter-garden-7b-beta.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| winter-garden-7b-beta.Q4_K.gguf | Q4_K | 4.07GB |
| winter-garden-7b-beta.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| winter-garden-7b-beta.Q4_1.gguf | Q4_1 | 4.24GB |
| winter-garden-7b-beta.Q5_0.gguf | Q5_0 | 4.65GB |
| winter-garden-7b-beta.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| winter-garden-7b-beta.Q5_K.gguf | Q5_K | 4.78GB |
| winter-garden-7b-beta.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| winter-garden-7b-beta.Q5_1.gguf | Q5_1 | 5.07GB |
| winter-garden-7b-beta.Q6_K.gguf | Q6_K | 5.53GB |
| winter-garden-7b-beta.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: cc-by-nc-4.0 tags:
- merge
- conversational
- multi-task pipeline_tag: text-generation
Winter Garden 7B - β - "The Writer"
It was mentioned that we are in the open ai dark winter; so I thought I would make myself a nice winter garden.
An experiment
I've merged four partitions successfully in the past, so lets go for 9! I started with:
- Mistral-7B-v0.1
and merged in
- ZySec-7B-v1
- LemonadeRP-4.5.3
- dpo-binarized-NeutrixOmnibe-7B
- Multi-Verse-RP-7B
- AlphaMonarch-7B
- opus-v1.2-7b
- Kunoichi-DPO-v2-7B
- Noromaid-7B-0.4-DPO
- ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
9-partition merge
All of the layers were partitioned in to 9 random bins. Alternating models were slerped at [0...1], and [1...0] gradients; except attention, which was slerped at 0.03.
This means that the model is still predominantly ordered around base mistral - including half of the input and output layers, and 28% of attention.
Other
Includes fast tokenizer.
Chat Template
There is currently a chat template for conversational turns. It may or may not be good for this model without more tuning. Initial tests show this model is a real talker and writer.
- If you prompt with
[WP] <prompt>\n\nit will take right off.
It doesn't seem to know ### Instruction: or <|im_start|>; <|user|> ,<|assistant|> works but tends to get quickly mixed up with html, and back and forth conversation devolves in to long narratives.
Scores
| Metric | Score |
|---|
- Created
- Sep 13, 2024
- Updated
- Sep 13, 2024