mradermacher
commited on
Commit
•
d60f7f8
1
Parent(s):
941ed7c
auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ tags:
|
|
20 |
static quants of https://huggingface.co/ryzen88/Llama-3-70b-Uncensored-Lumi-Tess-gradient
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
-
weighted/imatrix quants
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -33,8 +33,19 @@ more details, including on how to concatenate multi-part files.
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
|
|
|
|
|
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
|
|
|
|
|
|
|
|
38 |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
39 |
|
40 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
20 |
static quants of https://huggingface.co/ryzen88/Llama-3-70b-Uncensored-Lumi-Tess-gradient
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q2_K.gguf) | Q2_K | 26.5 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_M.gguf) | IQ3_M | 32.0 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
|
48 |
+
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
|
49 |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF/resolve/main/Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|