Upload folder using huggingface_hub
Browse files- .gitattributes +8 -0
- README.md +21 -0
- ScikitLLM-Model-IQ3_XXS.gguf +3 -0
- ScikitLLM-Model-IQ4_XS.gguf +3 -0
- ScikitLLM-Model-Q3_K_M.gguf +3 -0
- ScikitLLM-Model-Q4_K_M.gguf +3 -0
- ScikitLLM-Model-Q4_K_S.gguf +3 -0
- ScikitLLM-Model-Q5_K_M.gguf +3 -0
- ScikitLLM-Model-Q6_K.gguf +3 -0
- ScikitLLM-Model-Q8_0.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip 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 |
+
ScikitLLM-Model-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
ScikitLLM-Model-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
ScikitLLM-Model-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
ScikitLLM-Model-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
ScikitLLM-Model-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
ScikitLLM-Model-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
ScikitLLM-Model-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
ScikitLLM-Model-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Original model link: [Pclanglais/ScikitLLM-Model](https://huggingface.co/Pclanglais/ScikitLLM-Model)
|
2 |
+
|
3 |
+
For imatrix data generation, kalomaze's `groups_merged.txt` were used you can find it [here](https://github.com/ggerganov/llama.cpp/files/14194570/groups_merged.txt).
|
4 |
+
|
5 |
+
Original model README below.
|
6 |
+
|
7 |
+
***ScikitLLM*** is an LLM finetuned on writing references and code for the Scikit-Learn documentation.
|
8 |
+
|
9 |
+
Features of ScikitLLM includes:
|
10 |
+
* Support for RAG (three chunks)
|
11 |
+
* Sources and quotations using a modified version of the wiki syntax ("<ref>")
|
12 |
+
* Code samples and examples based on the code quoted in the chunks.
|
13 |
+
* Expanded knowledge/familiarity with the Scikit-Learn concepts and documentation.
|
14 |
+
|
15 |
+
## Training
|
16 |
+
|
17 |
+
ScikitLLM is based on Mistral-OpenHermes 7B, a pre-existing finetune version of Mistral 7B. OpenHermes already include many desired capacities for the end use, including instruction tuning, source analysis, and native support for the chatML syntax.
|
18 |
+
|
19 |
+
As a fine-tune of a fine-tune, ScikitLLM has been trained with a lower learning rate than is commonly used in fine-tuning projects.
|
20 |
+
|
21 |
+
|
ScikitLLM-Model-IQ3_XXS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8ad7fd494db6d29f5b57ecbe77f1311ec46626d07fba5479cef49a7c7d870fa
|
3 |
+
size 2827353088
|
ScikitLLM-Model-IQ4_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:395719263941ff995f3139a374daf667c48b2d5784a846db41398939a63e61a9
|
3 |
+
size 3907699584
|
ScikitLLM-Model-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:735c5c1d74435f9870c37e759d068db87b1773b984ee336ff6ad79d44263ab28
|
3 |
+
size 3518996544
|
ScikitLLM-Model-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa45f5f0d05674bec569b2b0e59ed5772ebe0262a37876e2c25fb05468096930
|
3 |
+
size 4368450688
|
ScikitLLM-Model-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d4aa57b253bd92e50a145795eaacc2a12e4dd1c814560f62e0d7dfcefe160b6
|
3 |
+
size 4140385408
|
ScikitLLM-Model-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59f2fc03eadfd10c317ae83ef5ee25aaa0ace3b8a3b0951a6b44f4d8c6631cbc
|
3 |
+
size 5131421824
|
ScikitLLM-Model-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86462a2903bb5a87bb54772250db1ab2fbc2219bfb0dc12cabeb0150aa2dfe32
|
3 |
+
size 5942078656
|
ScikitLLM-Model-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:528662b5d8bdb34d16f9224815e0ef1513f5fd76fbdd14d8845054b00ffacc80
|
3 |
+
size 7695875136
|