Hugging Face's logo

cjpais
/
llava-v1.6-vicuna-7b-gguf

Image-Text-to-Text
GGUF
llava
Model card Files Community
1
cjpais commited on
Commit
dcadd56
•
1 Parent(s): 850209b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -12,13 +12,13 @@ Updated quants and projector from [PR #5267](https://github.com/ggerganov/llama.
12
  ## Provided files
13
  | Name | Quant method | Bits | Size | Use case |
14
  | ---- | ---- | ---- | ---- | ----- |
15
- | [llava-v1.6-vicuna-7b.Q3_K_XS.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q3_K_XS.gguf) | Q3_K_XS | 3 | 2.99 GB| very small, high quality loss |
16
- | [llava-v1.6-vicuna-7b.Q3_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss |
17
- | [llava-v1.6-vicuna-7b.Q4_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended |
18
- | [llava-v1.6-vicuna-7b.Q5_K_S.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended |
19
- | [llava-v1.6-vicuna-7b.Q5_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended |
20
- | [llava-v1.6-vicuna-7b.Q6_K.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss |
21
- | [llava-v1.6-vicuna-7b.Q8_0.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended |
22
 
23
  <br>
24
  <br>
 
12
  ## Provided files
13
  | Name | Quant method | Bits | Size | Use case |
14
  | ---- | ---- | ---- | ---- | ----- |
15
+ | [llava-v1.6-vicuna-7b.Q3_K_XS.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q3_K_XS.gguf) | Q3_K_XS | 3 | 2.77 GB| very small, high quality loss |
16
+ | [llava-v1.6-vicuna-7b.Q3_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.3 GB| very small, high quality loss |
17
+ | [llava-v1.6-vicuna-7b.Q4_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| medium, balanced quality - recommended |
18
+ | [llava-v1.6-vicuna-7b.Q5_K_S.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
19
+ | [llava-v1.6-vicuna-7b.Q5_K_M.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| large, very low quality loss - recommended |
20
+ | [llava-v1.6-vicuna-7b.Q6_K.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss |
21
+ | [llava-v1.6-vicuna-7b.Q8_0.gguf](https://huggingface.co/cjpais/llava-v1.6-vicuna-7b-gguf/blob/main/llava-v1.6-vicuna-7b.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
22
 
23
  <br>
24
  <br>