Update README.md
Browse files
README.md
CHANGED
@@ -15,11 +15,37 @@ tags:
|
|
15 |
---
|
16 |
|
17 |
# Chocolatine-3B-Instruct-DPO-Revised-Q4_K_M-GGUF
|
|
|
18 |
Quantized q4_k_m GGUF version of the original model [`Chocolatine-3B-Instruct-DPO-Revised`](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-Revised)
|
19 |
-
can be used on a CPU device, compatible llama.cpp
|
20 |
-
now supported architecture by LM Studio.
|
21 |
Also ready for Raspberry Pi 5 8Gb.
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
### Limitations
|
25 |
|
|
|
15 |
---
|
16 |
|
17 |
# Chocolatine-3B-Instruct-DPO-Revised-Q4_K_M-GGUF
|
18 |
+
|
19 |
Quantized q4_k_m GGUF version of the original model [`Chocolatine-3B-Instruct-DPO-Revised`](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-Revised)
|
20 |
+
can be used on a CPU device, compatible [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
21 |
+
now supported architecture by [LM Studio](https://lmstudio.ai/).
|
22 |
Also ready for Raspberry Pi 5 8Gb.
|
23 |
|
24 |
+
### Ollama
|
25 |
+
|
26 |
+
[jpacifico/chocolatine-3b](https://ollama.com/jpacifico/chocolatine-3b)
|
27 |
+
|
28 |
+
Usage:
|
29 |
+
|
30 |
+
```bash
|
31 |
+
ollama run jpacifico/chocolatine-3b
|
32 |
+
```
|
33 |
+
|
34 |
+
Ollama *Modelfile* example :
|
35 |
+
|
36 |
+
```bash
|
37 |
+
FROM ./chocolatine-3b-instruct-dpo-revised-q4_k_m.gguf
|
38 |
+
TEMPLATE """{{ if .System }}<|system|>
|
39 |
+
{{ .System }}<|end|>
|
40 |
+
{{ end }}{{ if .Prompt }}<|user|>
|
41 |
+
{{ .Prompt }}<|end|>
|
42 |
+
{{ end }}<|assistant|>
|
43 |
+
{{ .Response }}<|end|>
|
44 |
+
"""
|
45 |
+
PARAMETER stop """{"stop": ["<|end|>","<|user|>","<|assistant|>"]}"""
|
46 |
+
SYSTEM """You are a friendly assistant called Chocolatine."""
|
47 |
+
```
|
48 |
+
|
49 |
|
50 |
### Limitations
|
51 |
|