Commit
•
1e3654f
1
Parent(s):
154d007
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -33,7 +33,9 @@ language:
|
|
| 33 |
|
| 34 |
## Run with LlamaEdge
|
| 35 |
|
| 36 |
-
- LlamaEdge version:
|
|
|
|
|
|
|
| 37 |
|
| 38 |
- Prompt template
|
| 39 |
|
|
@@ -43,11 +45,11 @@ language:
|
|
| 43 |
|
| 44 |
```text
|
| 45 |
<s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
|
| 46 |
-
```
|
| 47 |
|
| 48 |
- Context size: `128000`
|
| 49 |
|
| 50 |
-
- Run as LlamaEdge service
|
| 51 |
|
| 52 |
```bash
|
| 53 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5_K_M.gguf \
|
|
@@ -64,8 +66,8 @@ language:
|
|
| 64 |
llama-chat.wasm \
|
| 65 |
--prompt-template mistral-instruct \
|
| 66 |
--ctx-size 128000
|
| 67 |
-
```
|
| 68 |
-
|
| 69 |
## Quantized GGUF Models
|
| 70 |
|
| 71 |
| Name | Quant method | Bits | Size | Use case |
|
|
@@ -82,6 +84,6 @@ language:
|
|
| 82 |
| [Mistral-Nemo-Instruct-2407-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf) | Q5_K_S | 5 | 5 GB| large, low quality loss - recommended |
|
| 83 |
| [Mistral-Nemo-Instruct-2407-Q6_K.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K.gguf) | Q6_K | 6 | 5.95 GB| very large, extremely low quality loss |
|
| 84 |
| [Mistral-Nemo-Instruct-2407-Q8_0.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended |
|
| 85 |
-
| [Mistral-Nemo-Instruct-2407-f16.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f16.gguf) | f16 | 16 | 14.5 GB| |
|
| 86 |
|
| 87 |
*Quantized with llama.cpp b3405.*
|
|
|
|
| 33 |
|
| 34 |
## Run with LlamaEdge
|
| 35 |
|
| 36 |
+
- LlamaEdge version: coming soon
|
| 37 |
+
|
| 38 |
+
<!-- - LlamaEdge version: [v0.12.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.3)
|
| 39 |
|
| 40 |
- Prompt template
|
| 41 |
|
|
|
|
| 45 |
|
| 46 |
```text
|
| 47 |
<s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
|
| 48 |
+
``` -->
|
| 49 |
|
| 50 |
- Context size: `128000`
|
| 51 |
|
| 52 |
+
<!-- - Run as LlamaEdge service
|
| 53 |
|
| 54 |
```bash
|
| 55 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5_K_M.gguf \
|
|
|
|
| 66 |
llama-chat.wasm \
|
| 67 |
--prompt-template mistral-instruct \
|
| 68 |
--ctx-size 128000
|
| 69 |
+
``` -->
|
| 70 |
+
<!--
|
| 71 |
## Quantized GGUF Models
|
| 72 |
|
| 73 |
| Name | Quant method | Bits | Size | Use case |
|
|
|
|
| 84 |
| [Mistral-Nemo-Instruct-2407-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf) | Q5_K_S | 5 | 5 GB| large, low quality loss - recommended |
|
| 85 |
| [Mistral-Nemo-Instruct-2407-Q6_K.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K.gguf) | Q6_K | 6 | 5.95 GB| very large, extremely low quality loss |
|
| 86 |
| [Mistral-Nemo-Instruct-2407-Q8_0.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended |
|
| 87 |
+
| [Mistral-Nemo-Instruct-2407-f16.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f16.gguf) | f16 | 16 | 14.5 GB| | -->
|
| 88 |
|
| 89 |
*Quantized with llama.cpp b3405.*
|