LLukas22 commited on
Commit
909bf7b
1 Parent(s): ac2c519

Generated README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ tags:
6
+ - llm-rs
7
+ - ggml
8
+ pipeline_tag: text-generation
9
+ datasets:
10
+ - databricks/databricks-dolly-15k
11
+ ---
12
+
13
+ # GGML converted version of [Databricks](https://huggingface.co/databricks) Dolly-V2 models
14
+
15
+ ## Description
16
+
17
+ Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT paper, including brainstorming, classification, closed QA, generation, information extraction, open QA and summarization.
18
+
19
+
20
+ ## Converted Models
21
+ | Name | Based on | Type | Container | GGML Version |
22
+ |:--------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------|:-------|:------------|:---------------|
23
+ | [dolly-v2-12b-f16.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-12b-f16.bin) | [databricks/dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b) | F16 | GGML | V3 |
24
+ | [dolly-v2-12b-q4_0.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-12b-q4_0.bin) | [databricks/dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b) | Q4_0 | GGML | V3 |
25
+ | [dolly-v2-12b-q4_0-ggjt.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-12b-q4_0-ggjt.bin) | [databricks/dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b) | Q4_0 | GGJT | V3 |
26
+ | [dolly-v2-3b-f16.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-3b-f16.bin) | [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b) | F16 | GGML | V3 |
27
+ | [dolly-v2-3b-q4_0.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-3b-q4_0.bin) | [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b) | Q4_0 | GGML | V3 |
28
+ | [dolly-v2-3b-q4_0-ggjt.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-3b-q4_0-ggjt.bin) | [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b) | Q4_0 | GGJT | V3 |
29
+ | [dolly-v2-3b-q5_1-ggjt.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-3b-q5_1-ggjt.bin) | [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b) | Q5_1 | GGJT | V3 |
30
+ | [dolly-v2-7b-f16.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-7b-f16.bin) | [databricks/dolly-v2-7b](https://huggingface.co/databricks/dolly-v2-7b) | F16 | GGML | V3 |
31
+ | [dolly-v2-7b-q4_0.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-7b-q4_0.bin) | [databricks/dolly-v2-7b](https://huggingface.co/databricks/dolly-v2-7b) | Q4_0 | GGML | V3 |
32
+ | [dolly-v2-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-7b-q4_0-ggjt.bin) | [databricks/dolly-v2-7b](https://huggingface.co/databricks/dolly-v2-7b) | Q4_0 | GGJT | V3 |
33
+ | [dolly-v2-7b-q5_1-ggjt.bin](https://huggingface.co/rustformers/dolly-v2-ggml/blob/main/dolly-v2-7b-q5_1-ggjt.bin) | [databricks/dolly-v2-7b](https://huggingface.co/databricks/dolly-v2-7b) | Q5_1 | GGJT | V3 |
34
+
35
+ ## Usage
36
+
37
+ ### Python via [llm-rs](https://github.com/LLukas22/llm-rs-python):
38
+
39
+ #### Installation
40
+ Via pip: `pip install llm-rs`
41
+
42
+ #### Run inference
43
+ ```python
44
+ from llm_rs import AutoModel
45
+
46
+ #Load the model, define any model you like from the list above as the `model_file`
47
+ model = AutoModel.from_pretrained("rustformers/dolly-v2-ggml",model_file="dolly-v2-12b-q4_0-ggjt.bin")
48
+
49
+ #Generate
50
+ print(model.generate("The meaning of life is"))
51
+ ```
52
+
53
+ ### Rust via [Rustformers/llm](https://github.com/rustformers/llm):
54
+
55
+ #### Installation
56
+ ```
57
+ git clone --recurse-submodules https://github.com/rustformers/llm.git
58
+ cd llm
59
+ cargo build --release
60
+ ```
61
+
62
+ #### Run inference
63
+ ```
64
+ cargo run --release -- gptneox infer -m path/to/model.bin -p "Tell me how cool the Rust programming language is:"
65
+ ```