Initial GPTQ model commit
Browse files
README.md
CHANGED
@@ -31,11 +31,13 @@ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com
|
|
31 |
|
32 |
## Prompt template: Alpaca
|
33 |
|
34 |
-
```
|
|
|
35 |
|
36 |
### Instruction: {prompt}
|
37 |
|
38 |
### Response:
|
|
|
39 |
```
|
40 |
|
41 |
## Provided files
|
@@ -47,10 +49,10 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
47 |
| Branch | Filename | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With |
|
48 |
| ------ | -------- | ---- | ---------- | -------------------- | --------- | ------------------- | --------- |
|
49 |
| main | open-llama-7b-v2-open-instruct-GPTQ-4bit-128g.no-act.order.safetensors | 4 | 128 | False | 4.00 GB | True | GPTQ-for-LLaMa |
|
50 |
-
| gptq-4bit-32g-actorder_True | gptq_model-4bit-32g.safetensors | 4 | 32 | True | 4.28 GB | True |
|
51 |
-
| gptq-4bit-64g-actorder_True | gptq_model-4bit-64g.safetensors | 4 | 64 | True | 4.02 GB | True |
|
52 |
-
| gptq-4bit-128g-actorder_True | gptq_model-4bit-128g.safetensors | 4 | 128 | True | 3.90 GB | True |
|
53 |
-
| gptq-8bit--1g-actorder_True | gptq_model-8bit--1g.safetensors | 8 | -1 | True | 7.01 GB | False |
|
54 |
|
55 |
|
56 |
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
|
|
|
31 |
|
32 |
## Prompt template: Alpaca
|
33 |
|
34 |
+
```
|
35 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
36 |
|
37 |
### Instruction: {prompt}
|
38 |
|
39 |
### Response:
|
40 |
+
|
41 |
```
|
42 |
|
43 |
## Provided files
|
|
|
49 |
| Branch | Filename | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With |
|
50 |
| ------ | -------- | ---- | ---------- | -------------------- | --------- | ------------------- | --------- |
|
51 |
| main | open-llama-7b-v2-open-instruct-GPTQ-4bit-128g.no-act.order.safetensors | 4 | 128 | False | 4.00 GB | True | GPTQ-for-LLaMa |
|
52 |
+
| gptq-4bit-32g-actorder_True | gptq_model-4bit-32g.safetensors | 4 | 32 | True | 4.28 GB | True | AutoGPTQ |
|
53 |
+
| gptq-4bit-64g-actorder_True | gptq_model-4bit-64g.safetensors | 4 | 64 | True | 4.02 GB | True | AutoGPTQ |
|
54 |
+
| gptq-4bit-128g-actorder_True | gptq_model-4bit-128g.safetensors | 4 | 128 | True | 3.90 GB | True | AutoGPTQ |
|
55 |
+
| gptq-8bit--1g-actorder_True | gptq_model-8bit--1g.safetensors | 8 | -1 | True | 7.01 GB | False | AutoGPTQ |
|
56 |
|
57 |
|
58 |
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
|