auto-patch README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ quantized_by: mradermacher
|
|
18 |
static quants of https://huggingface.co/DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
-
weighted/imatrix quants
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -35,10 +35,15 @@ more details, including on how to concatenate multi-part files.
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | |
|
|
|
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | |
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
|
|
|
|
|
42 |
|
43 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
44 |
types (lower is better):
|
|
|
18 |
static quants of https://huggingface.co/DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-i1-GGUF
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF/resolve/main/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B.f16.gguf) | f16 | 2.6 | 16 bpw, overkill |
|
47 |
|
48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
49 |
types (lower is better):
|