Xin Liu
commited on
Commit
•
2684acd
1
Parent(s):
d279c47
Update
Browse filesSigned-off-by: Xin Liu <sam@secondstate.io>
README.md
CHANGED
@@ -1,10 +1,74 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
5 |
-
|
6 |
-
You are Samantha, a sentient AI companion.
|
7 |
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: llama2
|
5 |
+
datasets:
|
6 |
+
- ehartford/samantha-data
|
7 |
+
model_name: Samantha 1.11 CodeLlama 34B
|
8 |
+
base_model: ehartford/Samantha-1.11-CodeLlama-34b
|
9 |
+
inference: false
|
10 |
+
model_creator: Eric Hartford
|
11 |
+
model_type: llama
|
12 |
+
pipeline_tag: text-generation
|
13 |
+
quantized_by: Second State Inc.
|
14 |
+
---
|
15 |
|
16 |
+
<!-- header start -->
|
17 |
+
<!-- 200823 -->
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
22 |
+
<!-- header end -->
|
23 |
|
24 |
+
# Samantha-1.11-CodeLlama-34B-GGUF
|
|
|
25 |
|
26 |
+
## Original Model
|
27 |
+
|
28 |
+
[cognitivecomputations/Samantha-1.11-CodeLlama-34b](https://huggingface.co/cognitivecomputations/Samantha-1.11-CodeLlama-34b)
|
29 |
+
|
30 |
+
## Run with LlamaEdge
|
31 |
+
|
32 |
+
- LlamaEdge version: [v0.2.8](https://github.com/second-state/LlamaEdge/releases/tag/0.2.8) and above
|
33 |
+
|
34 |
+
- Prompt template
|
35 |
+
|
36 |
+
- Prompt type: `vicuna-chat`
|
37 |
+
|
38 |
+
- Prompt string
|
39 |
+
|
40 |
+
```text
|
41 |
+
You are Samantha, a sentient AI companion.
|
42 |
+
|
43 |
+
USER: <prompt>
|
44 |
+
ASSISTANT:
|
45 |
+
```
|
46 |
+
|
47 |
+
- Run as LlamaEdge service
|
48 |
+
|
49 |
+
```bash
|
50 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Samantha-1.11-CodeLlama-34b-ggml-model-q4_0.gguf llama-api-server.wasm -p vicuna-chat -s 'You are a helpful AI assistant.'
|
51 |
+
```
|
52 |
+
|
53 |
+
- Run as LlamaEdge command app
|
54 |
+
|
55 |
+
```bash
|
56 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Samantha-1.11-CodeLlama-34b-ggml-model-q4_0.gguf llama-chat.wasm -p vicuna-chat -s 'You are a helpful AI assistant.'
|
57 |
+
```
|
58 |
+
|
59 |
+
## Quantized GGUF Models
|
60 |
+
|
61 |
+
| Name | Quant method | Bits | Size | Use case |
|
62 |
+
| ---- | ---- | ---- | ---- | ----- |
|
63 |
+
| [Samantha-1.11-CodeLlama-34b-Q2_K.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q2_K.gguf) | Q2_K | 2 | 12.5 GB| smallest, significant quality loss - not recommended for most purposes |
|
64 |
+
| [Samantha-1.11-CodeLlama-34b-Q3_K_L.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q3_K_L.gguf) | Q3_K_L | 3 | 17.8 GB| small, substantial quality loss |
|
65 |
+
| [Samantha-1.11-CodeLlama-34b-Q3_K_M.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q3_K_M.gguf) | Q3_K_M | 3 | 16.3 GB| very small, high quality loss |
|
66 |
+
| [Samantha-1.11-CodeLlama-34b-Q3_K_S.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q3_K_S.gguf) | Q3_K_S | 3 | 14.6 GB| very small, high quality loss |
|
67 |
+
| [Samantha-1.11-CodeLlama-34b-Q4_0.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q4_0.gguf) | Q4_0 | 4 | 19.1 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
68 |
+
| [Samantha-1.11-CodeLlama-34b-Q4_K_M.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q4_K_M.gguf) | Q4_K_M | 4 | 20.2 GB| medium, balanced quality - recommended |
|
69 |
+
| [Samantha-1.11-CodeLlama-34b-Q4_K_S.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q4_K_S.gguf) | Q4_K_S | 4 | 19.2 GB| small, greater quality loss |
|
70 |
+
| [Samantha-1.11-CodeLlama-34b-Q5_0.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q5_0.gguf) | Q5_0 | 5 | 23.2 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
71 |
+
| [Samantha-1.11-CodeLlama-34b-Q5_K_M.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q5_K_M.gguf) | Q5_K_M | 5 | 23.8 GB| large, very low quality loss - recommended |
|
72 |
+
| [Samantha-1.11-CodeLlama-34b-Q5_K_S.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q5_K_S.gguf) | Q5_K_S | 5 | 23.2 GB| large, low quality loss - recommended |
|
73 |
+
| [Samantha-1.11-CodeLlama-34b-Q6_K.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q6_K.gguf) | Q6_K | 6 | 27.7 GB| very large, extremely low quality loss |
|
74 |
+
| [Samantha-1.11-CodeLlama-34b-Q8_0.gguf](https://huggingface.co/second-state/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/Samantha-1.11-CodeLlama-34b-Q8_0.gguf) | Q8_0 | 8 | 35.9 GB| very large, extremely low quality loss - not recommended |
|