Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- LFM2.5-1.2B-Thinking-Q8_0.gguf +3 -0
- 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
|
|
|
|
|
|
|
| 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 |
|