maximaverick commited on
Commit
08af9f7
verified
1 Parent(s): 7d57b9d

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. LFM2.5-1.2B-Thinking-Q8_0.gguf +3 -0
  3. README.md +3 -1
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  LFM2.5-1.2B-Thinking-F16.gguf filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  LFM2.5-1.2B-Thinking-F16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ LFM2.5-1.2B-Thinking-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LFM2.5-1.2B-Thinking-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f117689018d48dd883bf66b2793e15b083c3ecad6f8c54a840f3a1dcb35d0ac
3
+ size 1246253952
README.md CHANGED
@@ -42,7 +42,9 @@ The fine-tuning involved a vast amount of specialized financial data, moving awa
42
  ## Usage | 浣跨敤鏂规硶
43
 
44
  ### Option 1: LM Studio (Recommended)
45
- 1. Download the `.gguf` file.
 
 
46
  2. Import via `lms import` or Drag & Drop.
47
  3. The model is optimized for structured financial queries.
48
 
 
42
  ## Usage | 浣跨敤鏂规硶
43
 
44
  ### Option 1: LM Studio (Recommended)
45
+ 1. Download the **.gguf** file.
46
+ - `LFM2.5-1.2B-Thinking-F16.gguf`: Full precision (Best quality, ~2.3GB).
47
+ - `LFM2.5-1.2B-Thinking-Q8_0.gguf`: 8-bit quantization (Faster, smaller, ~1.3GB).
48
  2. Import via `lms import` or Drag & Drop.
49
  3. The model is optimized for structured financial queries.
50