Commit
•
a7f9f10
1
Parent(s):
d97acd2
Update README.md
Browse files
README.md
CHANGED
@@ -1,91 +1,91 @@
|
|
1 |
-
---
|
2 |
-
base_model: 01-ai/Yi-1.5-34B-Chat
|
3 |
-
inference: false
|
4 |
-
license: other
|
5 |
-
license_link: LICENSE
|
6 |
-
license_name: yi-license
|
7 |
-
model_creator: 01-ai
|
8 |
-
model_name: Yi-1.5-34B-Chat
|
9 |
-
model_type: yi
|
10 |
-
pipeline_tag: text-generation
|
11 |
-
quantized_by: Second State Inc.
|
12 |
-
---
|
13 |
-
|
14 |
-
<!-- header start -->
|
15 |
-
<!-- 200823 -->
|
16 |
-
<div style="width: auto; margin-left: auto; margin-right: auto">
|
17 |
-
<img src="https://github.com/
|
18 |
-
</div>
|
19 |
-
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
20 |
-
<!-- header end -->
|
21 |
-
|
22 |
-
# Yi-1.5-34B-Chat-GGUF
|
23 |
-
|
24 |
-
## Original Model
|
25 |
-
|
26 |
-
[01-ai/Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat)
|
27 |
-
|
28 |
-
## Run with LlamaEdge
|
29 |
-
|
30 |
-
- LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) and above
|
31 |
-
|
32 |
-
- Prompt template
|
33 |
-
|
34 |
-
- Prompt type: `chatml`
|
35 |
-
|
36 |
-
- Prompt string
|
37 |
-
|
38 |
-
```text
|
39 |
-
<|im_start|>system
|
40 |
-
{system_message}<|im_end|>
|
41 |
-
<|im_start|>user
|
42 |
-
{prompt}<|im_end|>
|
43 |
-
<|im_start|>assistant
|
44 |
-
```
|
45 |
-
|
46 |
-
- Reverse prompt: `<|im_end|>`
|
47 |
-
|
48 |
-
- Context size: `7168`
|
49 |
-
|
50 |
-
- Run as LlamaEdge service
|
51 |
-
|
52 |
-
```bash
|
53 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-Q5_K_M.gguf \
|
54 |
-
llama-api-server.wasm \
|
55 |
-
--prompt-template chatml \
|
56 |
-
--reverse-prompt '<|im_end|>' \
|
57 |
-
--ctx-size 7168 \
|
58 |
-
--model-name Yi-1.5-34B-Chat
|
59 |
-
```
|
60 |
-
|
61 |
-
- Run as LlamaEdge command app
|
62 |
-
|
63 |
-
```bash
|
64 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-Q5_K_M.gguf \
|
65 |
-
llama-chat.wasm \
|
66 |
-
--prompt-template chatml \
|
67 |
-
--reverse-prompt '<|im_end|>' \
|
68 |
-
--ctx-size 7168
|
69 |
-
```
|
70 |
-
|
71 |
-
## Quantized GGUF Models
|
72 |
-
|
73 |
-
| Name | Quant method | Bits | Size | Use case |
|
74 |
-
| ---- | ---- | ---- | ---- | ----- |
|
75 |
-
| [Yi-1.5-34B-Chat-Q2_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q2_K.gguf) | Q2_K | 2 |12.8 GB| smallest, significant quality loss - not recommended for most purposes |
|
76 |
-
| [Yi-1.5-34B-Chat-Q3_K_L.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 18.1 GB| small, substantial quality loss |
|
77 |
-
| [Yi-1.5-34B-Chat-Q3_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 16.7 GB| very small, high quality loss |
|
78 |
-
| [Yi-1.5-34B-Chat-Q3_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 15 GB| very small, high quality loss |
|
79 |
-
| [Yi-1.5-34B-Chat-Q4_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_0.gguf) | Q4_0 | 4 | 19.5 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
80 |
-
| [Yi-1.5-34B-Chat-Q4_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 20.7 GB| medium, balanced quality - recommended |
|
81 |
-
| [Yi-1.5-34B-Chat-Q4_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 19.6 GB| small, greater quality loss |
|
82 |
-
| [Yi-1.5-34B-Chat-Q5_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_0.gguf) | Q5_0 | 5 | 23.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
83 |
-
| [Yi-1.5-34B-Chat-Q5_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 23.4 GB| large, very low quality loss - recommended |
|
84 |
-
| [Yi-1.5-34B-Chat-Q5_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 23.7 GB| large, low quality loss - recommended |
|
85 |
-
| [Yi-1.5-34B-Chat-Q6_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q6_K.gguf) | Q6_K | 6 | 28.3 GB| very large, extremely low quality loss |
|
86 |
-
| [Yi-1.5-34B-Chat-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q8_0.gguf) | Q8_0 | 8 | 36.5 GB| very large, extremely low quality loss - not recommended |
|
87 |
-
| [Yi-1.5-34B-Chat-f16-00001-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00001-of-00003.gguf) | f16 | 16 | 32.2 GB| |
|
88 |
-
| [Yi-1.5-34B-Chat-f16-00002-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00002-of-00003.gguf) | f16 | 16 | 32.1 GB| |
|
89 |
-
| [Yi-1.5-34B-Chat-f16-00003-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00003-of-00003.gguf) | f16 | 16 | 4.48 GB| |
|
90 |
-
|
91 |
-
*Quantized with llama.cpp b2824*
|
|
|
1 |
+
---
|
2 |
+
base_model: 01-ai/Yi-1.5-34B-Chat
|
3 |
+
inference: false
|
4 |
+
license: other
|
5 |
+
license_link: LICENSE
|
6 |
+
license_name: yi-license
|
7 |
+
model_creator: 01-ai
|
8 |
+
model_name: Yi-1.5-34B-Chat
|
9 |
+
model_type: yi
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
quantized_by: Second State Inc.
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- header start -->
|
15 |
+
<!-- 200823 -->
|
16 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
17 |
+
<img src="https://github.com/GaiaNet-AI/.github/assets/45785633/d6976adc-f97d-4f86-a648-0f2f5c8e7eee" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
18 |
+
</div>
|
19 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
20 |
+
<!-- header end -->
|
21 |
+
|
22 |
+
# Yi-1.5-34B-Chat-GGUF
|
23 |
+
|
24 |
+
## Original Model
|
25 |
+
|
26 |
+
[01-ai/Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat)
|
27 |
+
|
28 |
+
## Run with LlamaEdge
|
29 |
+
|
30 |
+
- LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) and above
|
31 |
+
|
32 |
+
- Prompt template
|
33 |
+
|
34 |
+
- Prompt type: `chatml`
|
35 |
+
|
36 |
+
- Prompt string
|
37 |
+
|
38 |
+
```text
|
39 |
+
<|im_start|>system
|
40 |
+
{system_message}<|im_end|>
|
41 |
+
<|im_start|>user
|
42 |
+
{prompt}<|im_end|>
|
43 |
+
<|im_start|>assistant
|
44 |
+
```
|
45 |
+
|
46 |
+
- Reverse prompt: `<|im_end|>`
|
47 |
+
|
48 |
+
- Context size: `7168`
|
49 |
+
|
50 |
+
- Run as LlamaEdge service
|
51 |
+
|
52 |
+
```bash
|
53 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-Q5_K_M.gguf \
|
54 |
+
llama-api-server.wasm \
|
55 |
+
--prompt-template chatml \
|
56 |
+
--reverse-prompt '<|im_end|>' \
|
57 |
+
--ctx-size 7168 \
|
58 |
+
--model-name Yi-1.5-34B-Chat
|
59 |
+
```
|
60 |
+
|
61 |
+
- Run as LlamaEdge command app
|
62 |
+
|
63 |
+
```bash
|
64 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-Q5_K_M.gguf \
|
65 |
+
llama-chat.wasm \
|
66 |
+
--prompt-template chatml \
|
67 |
+
--reverse-prompt '<|im_end|>' \
|
68 |
+
--ctx-size 7168
|
69 |
+
```
|
70 |
+
|
71 |
+
## Quantized GGUF Models
|
72 |
+
|
73 |
+
| Name | Quant method | Bits | Size | Use case |
|
74 |
+
| ---- | ---- | ---- | ---- | ----- |
|
75 |
+
| [Yi-1.5-34B-Chat-Q2_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q2_K.gguf) | Q2_K | 2 |12.8 GB| smallest, significant quality loss - not recommended for most purposes |
|
76 |
+
| [Yi-1.5-34B-Chat-Q3_K_L.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 18.1 GB| small, substantial quality loss |
|
77 |
+
| [Yi-1.5-34B-Chat-Q3_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 16.7 GB| very small, high quality loss |
|
78 |
+
| [Yi-1.5-34B-Chat-Q3_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 15 GB| very small, high quality loss |
|
79 |
+
| [Yi-1.5-34B-Chat-Q4_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_0.gguf) | Q4_0 | 4 | 19.5 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
80 |
+
| [Yi-1.5-34B-Chat-Q4_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 20.7 GB| medium, balanced quality - recommended |
|
81 |
+
| [Yi-1.5-34B-Chat-Q4_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 19.6 GB| small, greater quality loss |
|
82 |
+
| [Yi-1.5-34B-Chat-Q5_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_0.gguf) | Q5_0 | 5 | 23.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
83 |
+
| [Yi-1.5-34B-Chat-Q5_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 23.4 GB| large, very low quality loss - recommended |
|
84 |
+
| [Yi-1.5-34B-Chat-Q5_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 23.7 GB| large, low quality loss - recommended |
|
85 |
+
| [Yi-1.5-34B-Chat-Q6_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q6_K.gguf) | Q6_K | 6 | 28.3 GB| very large, extremely low quality loss |
|
86 |
+
| [Yi-1.5-34B-Chat-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-Q8_0.gguf) | Q8_0 | 8 | 36.5 GB| very large, extremely low quality loss - not recommended |
|
87 |
+
| [Yi-1.5-34B-Chat-f16-00001-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00001-of-00003.gguf) | f16 | 16 | 32.2 GB| |
|
88 |
+
| [Yi-1.5-34B-Chat-f16-00002-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00002-of-00003.gguf) | f16 | 16 | 32.1 GB| |
|
89 |
+
| [Yi-1.5-34B-Chat-f16-00003-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-GGUF/blob/main/Yi-1.5-34B-Chat-f16-00003-of-00003.gguf) | f16 | 16 | 4.48 GB| |
|
90 |
+
|
91 |
+
*Quantized with llama.cpp b2824*
|