Downloads · 30 days
116
12% of all-time downloads
fblgit_-_UNAversal-2x7B-v1-gguf
RichardErkhov/fblgit_-_UNAversal-2x7B-v1-gguf
fblgit_-_UNAversal-2x7B-v1-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
1K
Public
Repo size
146 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf169 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 23, 2024
- Updated
- Sep 23, 2024
- SHA
- 818fc48c
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
UNAversal-2x7B-v1 - GGUF
- Model creator: https://huggingface.co/fblgit/
- Original model: https://huggingface.co/fblgit/UNAversal-2x7B-v1/
| Name | Quant method | Size |
|---|---|---|
| UNAversal-2x7B-v1.Q2_K.gguf | Q2_K | 4.43GB |
| UNAversal-2x7B-v1.IQ3_XS.gguf | IQ3_XS | 4.95GB |
| UNAversal-2x7B-v1.IQ3_S.gguf | IQ3_S | 5.22GB |
| UNAversal-2x7B-v1.Q3_K_S.gguf | Q3_K_S | 5.2GB |
| UNAversal-2x7B-v1.IQ3_M.gguf | IQ3_M | 5.35GB |
| UNAversal-2x7B-v1.Q3_K.gguf | Q3_K | 5.78GB |
| UNAversal-2x7B-v1.Q3_K_M.gguf | Q3_K_M | 5.78GB |
| UNAversal-2x7B-v1.Q3_K_L.gguf | Q3_K_L | 6.27GB |
| UNAversal-2x7B-v1.IQ4_XS.gguf | IQ4_XS | 6.5GB |
| UNAversal-2x7B-v1.Q4_0.gguf | Q4_0 | 6.78GB |
| UNAversal-2x7B-v1.IQ4_NL.gguf | IQ4_NL | 6.85GB |
| UNAversal-2x7B-v1.Q4_K_S.gguf | Q4_K_S | 6.84GB |
| UNAversal-2x7B-v1.Q4_K.gguf | Q4_K | 7.25GB |
| UNAversal-2x7B-v1.Q4_K_M.gguf | Q4_K_M | 7.25GB |
| UNAversal-2x7B-v1.Q4_1.gguf | Q4_1 | 7.52GB |
| UNAversal-2x7B-v1.Q5_0.gguf | Q5_0 | 8.26GB |
| UNAversal-2x7B-v1.Q5_K_S.gguf | Q5_K_S | 8.26GB |
| UNAversal-2x7B-v1.Q5_K.gguf | Q5_K | 8.51GB |
| UNAversal-2x7B-v1.Q5_K_M.gguf | Q5_K_M | 8.51GB |
| UNAversal-2x7B-v1.Q5_1.gguf | Q5_1 | 9.01GB |
| UNAversal-2x7B-v1.Q6_K.gguf | Q6_K | 9.84GB |
| UNAversal-2x7B-v1.Q8_0.gguf | Q8_0 | 12.75GB |
Original model description:
license: apache-2.0 tags:
- llama-factory
- lora
- generated_from_trainer model-index:
- name: UNAversal-2x7B-v1 results: []
UNAversal-2x7B-v1
Merely Phase 1 UNA, only MLP's and its kinda of a beta. The goal was to produce a small but powerful MoE.
This is a 2 MoE model, of 7B each expert. Based on intel-neural series v3.
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|---|
| arc_challenge | Yaml | none | 25 | acc | 0.7133 | ± | 0.0132 |
| none | 25 | acc_norm | 0.7235 | ± | 0.0131 | ||
| arc_easy | Yaml | none | 0 | acc | 0.8674 | ± | 0.0070 |
| none | 0 | acc_norm | 0.8291 | ± | 0.0077 | ||
| boolq | Yaml | none | 0 | acc | 0.8768 | ± | 0.0057 |
| lambada_openai | Yaml | none | 0 | perplexity | 3.6656 | ± | 0.0841 |
| none | 0 | acc | 0.7017 | ± | 0.0064 | ||
| mathqa | Yaml | none | 0 | acc | 0.3474 | ± | 0.0087 |
| none | 0 | acc_norm | 0.3585 | ± | 0.0088 | ||
| piqa | Yaml | none | 0 | acc | 0.8411 | ± | 0.0085 |
| none | 0 | acc_norm | 0.8526 | ± | 0.0083 | ||
| sciq | Yaml | none | 0 | acc | 0.9600 | ± | 0.0062 |
| none | 0 | acc_norm | 0.9370 | ± | 0.0077 |
- Created
- Sep 23, 2024
- Updated
- Sep 23, 2024