legraphista commited on
Commit
5efacef
β€’
1 Parent(s): 91af3e2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -27,7 +27,7 @@ tags:
27
  _Llama.cpp imatrix quantization of LLM360/K2-Chat_
28
 
29
  Original Model: [LLM360/K2-Chat](https://huggingface.co/LLM360/K2-Chat)
30
- Original dtype: `FP32` (`float32`)
31
  Quantized by: llama.cpp [b3051](https://github.com/ggerganov/llama.cpp/releases/tag/b3051)
32
  IMatrix dataset: [here](https://gist.githubusercontent.com/bartowski1182/eb213dccb3571f863da82e99418f81e8/raw/b2869d80f5c16fd7082594248e80144677736635/calibration_datav3.txt)
33
 
@@ -53,7 +53,7 @@ Link: [here](https://huggingface.co/legraphista/K2-Chat-IMat-GGUF/blob/main/imat
53
  ### Common Quants
54
  | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
55
  | -------- | ---------- | --------- | ------ | ------------ | -------- |
56
- | K2-Chat.Q8_0 | Q8_0 | - | ⏳ Processing | βšͺ Static | -
57
  | K2-Chat.Q6_K | Q6_K | - | ⏳ Processing | βšͺ Static | -
58
  | K2-Chat.Q4_K | Q4_K | - | ⏳ Processing | 🟒 IMatrix | -
59
  | K2-Chat.Q3_K | Q3_K | - | ⏳ Processing | 🟒 IMatrix | -
@@ -63,9 +63,8 @@ Link: [here](https://huggingface.co/legraphista/K2-Chat-IMat-GGUF/blob/main/imat
63
  ### All Quants
64
  | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
65
  | -------- | ---------- | --------- | ------ | ------------ | -------- |
66
- | K2-Chat.BF16 | BF16 | - | ⏳ Processing | βšͺ Static | -
67
  | K2-Chat.FP16 | F16 | - | ⏳ Processing | βšͺ Static | -
68
- | K2-Chat.Q8_0 | Q8_0 | - | ⏳ Processing | βšͺ Static | -
69
  | K2-Chat.Q6_K | Q6_K | - | ⏳ Processing | βšͺ Static | -
70
  | K2-Chat.Q5_K | Q5_K | - | ⏳ Processing | βšͺ Static | -
71
  | K2-Chat.Q5_K_S | Q5_K_S | - | ⏳ Processing | βšͺ Static | -
 
27
  _Llama.cpp imatrix quantization of LLM360/K2-Chat_
28
 
29
  Original Model: [LLM360/K2-Chat](https://huggingface.co/LLM360/K2-Chat)
30
+ Original dtype: `FP16` (`float16`)
31
  Quantized by: llama.cpp [b3051](https://github.com/ggerganov/llama.cpp/releases/tag/b3051)
32
  IMatrix dataset: [here](https://gist.githubusercontent.com/bartowski1182/eb213dccb3571f863da82e99418f81e8/raw/b2869d80f5c16fd7082594248e80144677736635/calibration_datav3.txt)
33
 
 
53
  ### Common Quants
54
  | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
55
  | -------- | ---------- | --------- | ------ | ------------ | -------- |
56
+ | [K2-Chat.Q8_0/*](https://huggingface.co/legraphista/K2-Chat-IMat-GGUF/tree/main/K2-Chat.Q8_0) | Q8_0 | 69.37GB | βœ… Available | βšͺ Static | βœ‚ Yes
57
  | K2-Chat.Q6_K | Q6_K | - | ⏳ Processing | βšͺ Static | -
58
  | K2-Chat.Q4_K | Q4_K | - | ⏳ Processing | 🟒 IMatrix | -
59
  | K2-Chat.Q3_K | Q3_K | - | ⏳ Processing | 🟒 IMatrix | -
 
63
  ### All Quants
64
  | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
65
  | -------- | ---------- | --------- | ------ | ------------ | -------- |
 
66
  | K2-Chat.FP16 | F16 | - | ⏳ Processing | βšͺ Static | -
67
+ | [K2-Chat.Q8_0/*](https://huggingface.co/legraphista/K2-Chat-IMat-GGUF/tree/main/K2-Chat.Q8_0) | Q8_0 | 69.37GB | βœ… Available | βšͺ Static | βœ‚ Yes
68
  | K2-Chat.Q6_K | Q6_K | - | ⏳ Processing | βšͺ Static | -
69
  | K2-Chat.Q5_K | Q5_K | - | ⏳ Processing | βšͺ Static | -
70
  | K2-Chat.Q5_K_S | Q5_K_S | - | ⏳ Processing | βšͺ Static | -