Commit
•
71da97c
1
Parent(s):
6eb522f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: meta-llama/Llama-3.2-
|
| 3 |
license: llama3.2
|
| 4 |
model_creator: meta
|
| 5 |
-
model_name: Llama-3.2-
|
| 6 |
quantized_by: Second State Inc.
|
| 7 |
language:
|
| 8 |
- en
|
|
@@ -62,7 +62,7 @@ tags:
|
|
| 62 |
- Run as LlamaEdge service
|
| 63 |
|
| 64 |
```bash
|
| 65 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-
|
| 66 |
llama-api-server.wasm \
|
| 67 |
--prompt-template llama-3-chat \
|
| 68 |
--ctx-size 128000 \
|
|
@@ -72,7 +72,7 @@ tags:
|
|
| 72 |
- Run as LlamaEdge command app
|
| 73 |
|
| 74 |
```bash
|
| 75 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-
|
| 76 |
llama-chat.wasm \
|
| 77 |
--prompt-template llama-3-chat \
|
| 78 |
--ctx-size 128000
|
|
@@ -82,18 +82,18 @@ tags:
|
|
| 82 |
|
| 83 |
| Name | Quant method | Bits | Size | Use case |
|
| 84 |
| ---- | ---- | ---- | ---- | ----- |
|
| 85 |
-
| [Llama-3.2-
|
| 86 |
-
| [Llama-3.2-
|
| 87 |
-
| [Llama-3.2-
|
| 88 |
-
| [Llama-3.2-
|
| 89 |
-
| [Llama-3.2-
|
| 90 |
-
| [Llama-3.2-
|
| 91 |
-
| [Llama-3.2-
|
| 92 |
-
| [Llama-3.2-
|
| 93 |
-
| [Llama-3.2-
|
| 94 |
-
| [Llama-3.2-
|
| 95 |
-
| [Llama-3.2-
|
| 96 |
-
| [Llama-3.2-
|
| 97 |
-
| [Llama-3.2-
|
| 98 |
|
| 99 |
*Quantized with llama.cpp b3807*
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-3B-Instruct
|
| 3 |
license: llama3.2
|
| 4 |
model_creator: meta
|
| 5 |
+
model_name: Llama-3.2-3B-Instruct
|
| 6 |
quantized_by: Second State Inc.
|
| 7 |
language:
|
| 8 |
- en
|
|
|
|
| 62 |
- Run as LlamaEdge service
|
| 63 |
|
| 64 |
```bash
|
| 65 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
|
| 66 |
llama-api-server.wasm \
|
| 67 |
--prompt-template llama-3-chat \
|
| 68 |
--ctx-size 128000 \
|
|
|
|
| 72 |
- Run as LlamaEdge command app
|
| 73 |
|
| 74 |
```bash
|
| 75 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
|
| 76 |
llama-chat.wasm \
|
| 77 |
--prompt-template llama-3-chat \
|
| 78 |
--ctx-size 128000
|
|
|
|
| 82 |
|
| 83 |
| Name | Quant method | Bits | Size | Use case |
|
| 84 |
| ---- | ---- | ---- | ---- | ----- |
|
| 85 |
+
| [Llama-3.2-3B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q2_K.gguf) | Q2_K | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes |
|
| 86 |
+
| [Llama-3.2-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss |
|
| 87 |
+
| [Llama-3.2-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss |
|
| 88 |
+
| [Llama-3.2-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss |
|
| 89 |
+
| [Llama-3.2-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 90 |
+
| [Llama-3.2-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended |
|
| 91 |
+
| [Llama-3.2-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss |
|
| 92 |
+
| [Llama-3.2-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 93 |
+
| [Llama-3.2-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended |
|
| 94 |
+
| [Llama-3.2-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended |
|
| 95 |
+
| [Llama-3.2-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.02 GB| very large, extremely low quality loss |
|
| 96 |
+
| [Llama-3.2-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| very large, extremely low quality loss - not recommended |
|
| 97 |
+
| [Llama-3.2-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-f16.gguf) | f16 | 16 | 2.48 GB| |
|
| 98 |
|
| 99 |
*Quantized with llama.cpp b3807*
|