Hugging Face's logo

second-state
/
Llama-3-8B-Japanese-Instruct-GGUF

Text Generation
GGUF
English
Japanese
conversational
Model card Files Community
apepkuss79 commited on
Commit
1802986
•
1 Parent(s): 780a092

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -20,7 +20,7 @@ language:
20
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
  <!-- header end -->
22
 
23
- # Llama3-8B-Japanese-Chat-GGUF
24
 
25
  ## Original Model
26
 
@@ -68,23 +68,23 @@ language:
68
  --prompt-template llama-3-chat \
69
  --ctx-size 4096
70
  ```
71
- <!--
72
  ## Quantized GGUF Models
73
 
74
  | Name | Quant method | Bits | Size | Use case |
75
  | ---- | ---- | ---- | ---- | ----- |
76
- | [Llama3-8B-Japanese-Chat-Q2_K.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
77
- | [Llama3-8B-Japanese-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
78
- | [Llama3-8B-Japanese-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
79
- | [Llama3-8B-Japanese-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
80
- | [Llama3-8B-Japanese-Chat-Q4_0.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
81
- | [Llama3-8B-Japanese-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
82
- | [Llama3-8B-Japanese-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
83
- | [Llama3-8B-Japanese-Chat-Q5_0.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
84
- | [Llama3-8B-Japanese-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
85
- | [Llama3-8B-Japanese-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
86
- | [Llama3-8B-Japanese-Chat-Q6_K.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
87
- | [Llama3-8B-Japanese-Chat-Q8_0.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
88
- | [Llama3-8B-Japanese-Chat-f16.gguf](https://huggingface.co/second-state/Llama3-8B-Japanese-Chat-GGUF/blob/main/Llama3-8B-Japanese-Chat-f16.gguf) | f16 | 16 | 16.1 GB| | -->
89
 
90
  *Quantized with llama.cpp b2824.*
 
20
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
  <!-- header end -->
22
 
23
+ # Llama-3-8B-Japanese-Instruct-GGUF
24
 
25
  ## Original Model
26
 
 
68
  --prompt-template llama-3-chat \
69
  --ctx-size 4096
70
  ```
71
+
72
  ## Quantized GGUF Models
73
 
74
  | Name | Quant method | Bits | Size | Use case |
75
  | ---- | ---- | ---- | ---- | ----- |
76
+ | [Llama-3-8B-Japanese-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
77
+ | [Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
78
+ | [Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
79
+ | [Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
80
+ | [Llama-3-8B-Japanese-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
81
+ | [Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
82
+ | [Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
83
+ | [Llama-3-8B-Japanese-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
84
+ | [Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
85
+ | [Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
86
+ | [Llama-3-8B-Japanese-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
87
+ | [Llama-3-8B-Japanese-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
88
+ | [Llama-3-8B-Japanese-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-f16.gguf) | f16 | 16 | 16.1 GB| |
89
 
90
  *Quantized with llama.cpp b2824.*