Upload README.md
Browse files
README.md
CHANGED
@@ -10,6 +10,18 @@ model_creator: AIDC-ai-business
|
|
10 |
model_name: Marcoroni 7b
|
11 |
model_type: llama
|
12 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
quantized_by: TheBloke
|
14 |
---
|
15 |
|
@@ -61,17 +73,23 @@ Here is an incomplate list of clients and libraries that are known to support GG
|
|
61 |
<!-- repositories-available start -->
|
62 |
## Repositories available
|
63 |
|
|
|
64 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Marcoroni-7b-GPTQ)
|
65 |
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Marcoroni-7b-GGUF)
|
66 |
* [AIDC-ai-business's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AIDC-ai-business/Marcoroni-7b)
|
67 |
<!-- repositories-available end -->
|
68 |
|
69 |
<!-- prompt-template start -->
|
70 |
-
## Prompt template:
|
71 |
|
72 |
```
|
|
|
|
|
|
|
73 |
{prompt}
|
74 |
|
|
|
|
|
75 |
```
|
76 |
|
77 |
<!-- prompt-template end -->
|
@@ -193,7 +211,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
|
|
193 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
194 |
|
195 |
```shell
|
196 |
-
./main -ngl 32 -m marcoroni-7b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
|
197 |
```
|
198 |
|
199 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|
|
|
10 |
model_name: Marcoroni 7b
|
11 |
model_type: llama
|
12 |
pipeline_tag: text-generation
|
13 |
+
prompt_template: 'Below is an instruction that describes a task. Write a response
|
14 |
+
that appropriately completes the request.
|
15 |
+
|
16 |
+
|
17 |
+
### Instruction:
|
18 |
+
|
19 |
+
{prompt}
|
20 |
+
|
21 |
+
|
22 |
+
### Response:
|
23 |
+
|
24 |
+
'
|
25 |
quantized_by: TheBloke
|
26 |
---
|
27 |
|
|
|
73 |
<!-- repositories-available start -->
|
74 |
## Repositories available
|
75 |
|
76 |
+
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Marcoroni-7b-AWQ)
|
77 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Marcoroni-7b-GPTQ)
|
78 |
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Marcoroni-7b-GGUF)
|
79 |
* [AIDC-ai-business's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AIDC-ai-business/Marcoroni-7b)
|
80 |
<!-- repositories-available end -->
|
81 |
|
82 |
<!-- prompt-template start -->
|
83 |
+
## Prompt template: Alpaca
|
84 |
|
85 |
```
|
86 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
87 |
+
|
88 |
+
### Instruction:
|
89 |
{prompt}
|
90 |
|
91 |
+
### Response:
|
92 |
+
|
93 |
```
|
94 |
|
95 |
<!-- prompt-template end -->
|
|
|
211 |
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
|
212 |
|
213 |
```shell
|
214 |
+
./main -ngl 32 -m marcoroni-7b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
|
215 |
```
|
216 |
|
217 |
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
|