hudsongouge commited on
Commit
de84515
·
1 Parent(s): 8eb0a74

add other quants

Browse files
README.md CHANGED
@@ -18,8 +18,10 @@ This repository contains the Chatter-70M model, a lightweight casual chat langua
18
 
19
  ## Model Variants
20
 
21
- - `model_q4_k_m.gguf`: 4-bit quantized version optimized for efficiency
22
- - `model_fp16.gguf`: 16-bit floating point version
 
 
23
  - `model.safetensors`: Original model weights in SafeTensors format
24
 
25
  ## Configuration Files
 
18
 
19
  ## Model Variants
20
 
21
+ - `model-Q4_K_M.gguf`: 4-bit quantized version
22
+ - `model-Q6_K.gguf`: 6-bit quantized version
23
+ - `model-Q8_0.gguf`: 8-bit quantized version
24
+ - `model-FP16.gguf`: 16-bit floating point version
25
  - `model.safetensors`: Original model weights in SafeTensors format
26
 
27
  ## Configuration Files
model_fp16.gguf → model-FP16.gguf RENAMED
File without changes
model_q4_k_m.gguf → model-Q4_K_M.gguf RENAMED
File without changes
model-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e94a57998d0ff4390b58e8010f9919b905d57dd7a3002b7fea296471652082
3
+ size 58747808
model-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb568f72e3fee2a1d6f0f96b93ca36c9d2b7cfc3f392c6b3594bb01e652f92c
3
+ size 75826080