Hugging Face's logo

alvarobartt
/
UltraCM-13B-GGUF

Text Generation
Transformers
GGUF
English
dpo
rlaif
preference
ultrafeedback
Model card Files Community
alvarobartt HF staff commited on
Commit
cb239dd
·
1 Parent(s): 96a3b30

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -44,14 +44,16 @@ and also heavily inspired by [TheBloke](https://huggingface.co/TheBloke) work on
44
 
45
  ### Model Files
46
 
 
 
47
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
48
  | ---- | ---- | ---- | ---- | ---- | ----- |
49
- | [UltraCM-13b.q4_0.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
50
  | [UltraCM-13b.q4_k_s.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_k_s.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
51
  | [UltraCM-13b.q4_k_m.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_k_m.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
52
- | [UltraCM-13b.q5_0.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
53
  | [UltraCM-13b.q5_k_s.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_k_s.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
54
- | [UltraCM-13b.q5_k_m.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_k_m.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
55
 
56
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
57
 
 
44
 
45
  ### Model Files
46
 
47
+ ## Provided files
48
+
49
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
50
  | ---- | ---- | ---- | ---- | ---- | ----- |
51
+ | [UltraCM-13b.q4_0.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
  | [UltraCM-13b.q4_k_s.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_k_s.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
53
  | [UltraCM-13b.q4_k_m.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q4_k_m.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
54
+ | [UltraCM-13b.q5_0.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
  | [UltraCM-13b.q5_k_s.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_k_s.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
56
+ | [UltraCM-13b.q5_k_m.gguf](https://huggingface.co/alvarobartt/UltraCM-13b-GGUF/blob/main/UltraCM-13b.q5_k_m.gguf) Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
57
 
58
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
59