auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -37,10 +37,21 @@ more details, including on how to concatenate multi-part files.
|
|
| 37 |
|
| 38 |
| Link | Type | Size/GB | Notes |
|
| 39 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality |
|
|
|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | |
|
|
|
|
|
|
|
|
|
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality |
|
|
|
|
|
|
|
| 44 |
|
| 45 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 46 |
types (lower is better):
|
|
|
|
| 37 |
|
| 38 |
| Link | Type | Size/GB | Notes |
|
| 39 |
|:-----|:-----|--------:|:------|
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality |
|
| 45 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better |
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | |
|
| 52 |
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality |
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Cypher-CoT-1.8B-i1-GGUF/resolve/main/Cypher-CoT-1.8B.i1-Q6_K.gguf) | i1-Q6_K | 1.6 | practically like static Q6_K |
|
| 55 |
|
| 56 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 57 |
types (lower is better):
|