Hugging Face's logo

mradermacher
/
llama-2-7b-RomanUrduEng-tuned-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
f583fe8
·
verified ·
1 Parent(s): c16b842

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -32,10 +32,14 @@ more details, including on how to concatenate multi-part files.
32
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
33
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
34
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
35
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
36
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
38
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
32
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
33
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
34
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
36
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
37
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
40
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/llama-2-7b-RomanUrduEng-tuned-GGUF/resolve/main/llama-2-7b-RomanUrduEng-tuned.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):