Hugging Face's logo

wambugu71
/
SwahiliInstruct-v0.1-GGUF

GGUF
English
Swahili
text-generation-inference
Inference Endpoints
conversational
Model card Files Community
Kennedy wambugu commited on
Commit
8f4d2cd
·
verified ·
1 Parent(s): 8d85454

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -17,7 +17,6 @@ This repo contains models from LLM `SwahiliInstruct-v0.1` in GGUF format i
17
 
18
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
19
  | ---- | ---- | ---- | ---- | ---- | ----- |
20
-
21
  | [swahiliinstruct-v0.1.Q3_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
22
  | [swahiliinstruct-v0.1.Q4_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
23
  |[swahiliinstruct-v0.1.Q5_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
 
17
 
18
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
19
  | ---- | ---- | ---- | ---- | ---- | ----- |
 
20
  | [swahiliinstruct-v0.1.Q3_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
21
  | [swahiliinstruct-v0.1.Q4_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
22
  |[swahiliinstruct-v0.1.Q5_K_M.gguf](https://huggingface.co/wambugu1738/SwahiliInstruct-v0.1-GGUF/blob/main/swahiliinstruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |