Hugging Face's logo

mradermacher
/
telugu-llama-7b-instruct-v0.1-GGUF

Transformers
GGUF
English
Telugu
conversational
Model card Files Community
mradermacher commited on
Commit
8c119ed
·
verified ·
1 Parent(s): f05c724

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -34,11 +34,14 @@ more details, including on how to concatenate multi-part files.
34
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
35
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.8 | |
 
37
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.9 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q6_K.gguf) | Q6_K | 5.7 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
34
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
35
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.8 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.8 | |
38
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.9 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.0 | |
42
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q6_K.gguf) | Q6_K | 5.7 | very good quality |
43
  | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/telugu-llama-7b-instruct-v0.1-GGUF/resolve/main/telugu-llama-7b-instruct-v0.1.f16.gguf) | f16 | 13.9 | 16 bpw, overkill |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):