Downloads · 30 days
26
11% of all-time downloads
RichardErkhov/Mihaiii_-_Pallas-0.5-gguf
Mihaiii_-_Pallas-0.5-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.
Downloads · 30 days
26
11% of all-time downloads
All-time downloads
231
Public
Repo size
389 GB
Likes
0
Public
Click a slice to open those files.
.gguf451 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Pallas-0.5 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Pallas-0.5.Q2_K.gguf | Q2_K | 11.94GB |
| Pallas-0.5.IQ3_XS.gguf | IQ3_XS | 13.26GB |
| Pallas-0.5.IQ3_S.gguf | IQ3_S | 13.99GB |
| Pallas-0.5.Q3_K_S.gguf | Q3_K_S | 13.93GB |
| Pallas-0.5.IQ3_M.gguf | IQ3_M | 14.5GB |
| Pallas-0.5.Q3_K.gguf | Q3_K | 15.51GB |
| Pallas-0.5.Q3_K_M.gguf | Q3_K_M | 15.51GB |
| Pallas-0.5.Q3_K_L.gguf | Q3_K_L | 16.89GB |
| Pallas-0.5.IQ4_XS.gguf | IQ4_XS | 17.36GB |
| Pallas-0.5.Q4_0.gguf | Q4_0 | 18.13GB |
| Pallas-0.5.IQ4_NL.gguf | IQ4_NL | 18.3GB |
| Pallas-0.5.Q4_K_S.gguf | Q4_K_S | 18.25GB |
| Pallas-0.5.Q4_K.gguf | Q4_K | 19.24GB |
| Pallas-0.5.Q4_K_M.gguf | Q4_K_M | 19.24GB |
| Pallas-0.5.Q4_1.gguf | Q4_1 | 20.1GB |
| Pallas-0.5.Q5_0.gguf | Q5_0 | 22.08GB |
| Pallas-0.5.Q5_K_S.gguf | Q5_K_S | 22.08GB |
| Pallas-0.5.Q5_K.gguf | Q5_K | 22.65GB |
| Pallas-0.5.Q5_K_M.gguf | Q5_K_M | 22.65GB |
| Pallas-0.5.Q5_1.gguf | Q5_1 | 24.05GB |
| Pallas-0.5.Q6_K.gguf | Q6_K | 26.28GB |
| Pallas-0.5.Q8_0.gguf | Q8_0 | 34.03GB |
base_model: migtissera/Tess-34B-v1.4 inference: false license: other license_name: yi-license license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE metrics:
An instruct based fine tune of migtissera/Tess-34B-v1.4.
It works well with long system prompts.
It isn't generic in a sense that it shouldn't be used for story telling, for example, but only for reasoning and text comprehension.
This model is trained on a private dataset. The high GSM8K score is NOT because of the MetaMath dataset.
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
Quants:
LoneStriker/Pallas-0.5-3.0bpw-h6-exl2
LoneStriker/Pallas-0.5-4.0bpw-h6-exl2
LoneStriker/Pallas-0.5-4.65bpw-h6-exl2
LoneStriker/Pallas-0.5-5.0bpw-h6-exl2