Hugging Face's logo

gaianet
/
Yi-1.5-34B-Chat-16K-GGUF

Text Generation
GGUF
conversational
Model card Files Community
apepkuss79 commited on
Commit
cf07c34
·
verified ·
1 Parent(s): 252e993

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -21
README.md CHANGED
@@ -25,6 +25,10 @@ quantized_by: Second State Inc.
25
 
26
  prompt template: `chatml`
27
 
 
 
 
 
28
  **Context size**
29
 
30
  chat_ctx_size: `16384`
@@ -35,24 +39,4 @@ chat_ctx_size: `16384`
35
 
36
  - Customize your node: https://docs.gaianet.ai/node-guide/customize
37
 
38
- ## Quantized GGUF Models
39
-
40
- | Name | Quant method | Bits | Size | Use case |
41
- | ---- | ---- | ---- | ---- | ----- |
42
- | [Yi-1.5-34B-Chat-16K-Q2_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q2_K.gguf) | Q2_K | 2 |12.8 GB| smallest, significant quality loss - not recommended for most purposes |
43
- | [Yi-1.5-34B-Chat-16K-Q3_K_L.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_L.gguf) | Q3_K_L | 3 | 18.1 GB| small, substantial quality loss |
44
- | [Yi-1.5-34B-Chat-16K-Q3_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_M.gguf) | Q3_K_M | 3 | 16.7 GB| very small, high quality loss |
45
- | [Yi-1.5-34B-Chat-16K-Q3_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_S.gguf) | Q3_K_S | 3 | 15 GB| very small, high quality loss |
46
- | [Yi-1.5-34B-Chat-16K-Q4_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_0.gguf) | Q4_0 | 4 | 19.5 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
47
- | [Yi-1.5-34B-Chat-16K-Q4_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_M.gguf) | Q4_K_M | 4 | 20.7 GB| medium, balanced quality - recommended |
48
- | [Yi-1.5-34B-Chat-16K-Q4_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_S.gguf) | Q4_K_S | 4 | 19.6 GB| small, greater quality loss |
49
- | [Yi-1.5-34B-Chat-16K-Q5_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_0.gguf) | Q5_0 | 5 | 23.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
50
- | [Yi-1.5-34B-Chat-16K-Q5_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_M.gguf) | Q5_K_M | 5 | 24.3 GB| large, very low quality loss - recommended |
51
- | [Yi-1.5-34B-Chat-16K-Q5_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_S.gguf) | Q5_K_S | 5 | 23.7 GB| large, low quality loss - recommended |
52
- | [Yi-1.5-34B-Chat-16K-Q6_K.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q6_K.gguf) | Q6_K | 6 | 28.2 GB| very large, extremely low quality loss |
53
- | [Yi-1.5-34B-Chat-16K-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q8_0.gguf) | Q8_0 | 8 | 36.5 GB| very large, extremely low quality loss - not recommended |
54
- | [Yi-1.5-34B-Chat-16K-f16-00001-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00001-of-00003.gguf) | f16 | 16 | 32.2 GB| |
55
- | [Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf) | f16 | 16 | 32.1 GB| |
56
- | [Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf](https://huggingface.co/gaianet/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf) | f16 | 16 | 4.48 GB| |
57
-
58
- *Quantized with llama.cpp b2824*
 
25
 
26
  prompt template: `chatml`
27
 
28
+ **Reverse prompt**
29
+
30
+ reverse prompt: `<|im_end|>`
31
+
32
  **Context size**
33
 
34
  chat_ctx_size: `16384`
 
39
 
40
  - Customize your node: https://docs.gaianet.ai/node-guide/customize
41
 
42
+ *Quantized with llama.cpp b3135*