RichardErkhov
commited on
Commit
•
e9df04c
1
Parent(s):
fe014ab
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
llama2-7b-chat-hf-v3 - GGUF
|
11 |
+
- Model creator: https://huggingface.co/TheTravellingEngineer/
|
12 |
+
- Original model: https://huggingface.co/TheTravellingEngineer/llama2-7b-chat-hf-v3/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [llama2-7b-chat-hf-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q2_K.gguf) | Q2_K | 2.36GB |
|
18 |
+
| [llama2-7b-chat-hf-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
|
19 |
+
| [llama2-7b-chat-hf-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.IQ3_S.gguf) | IQ3_S | 2.75GB |
|
20 |
+
| [llama2-7b-chat-hf-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
|
21 |
+
| [llama2-7b-chat-hf-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.IQ3_M.gguf) | IQ3_M | 2.9GB |
|
22 |
+
| [llama2-7b-chat-hf-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q3_K.gguf) | Q3_K | 3.07GB |
|
23 |
+
| [llama2-7b-chat-hf-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
|
24 |
+
| [llama2-7b-chat-hf-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
|
25 |
+
| [llama2-7b-chat-hf-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
|
26 |
+
| [llama2-7b-chat-hf-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q4_0.gguf) | Q4_0 | 3.56GB |
|
27 |
+
| [llama2-7b-chat-hf-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
|
28 |
+
| [llama2-7b-chat-hf-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
|
29 |
+
| [llama2-7b-chat-hf-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q4_K.gguf) | Q4_K | 3.8GB |
|
30 |
+
| [llama2-7b-chat-hf-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
|
31 |
+
| [llama2-7b-chat-hf-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q4_1.gguf) | Q4_1 | 3.95GB |
|
32 |
+
| [llama2-7b-chat-hf-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q5_0.gguf) | Q5_0 | 4.33GB |
|
33 |
+
| [llama2-7b-chat-hf-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
|
34 |
+
| [llama2-7b-chat-hf-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q5_K.gguf) | Q5_K | 4.45GB |
|
35 |
+
| [llama2-7b-chat-hf-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
|
36 |
+
| [llama2-7b-chat-hf-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q5_1.gguf) | Q5_1 | 4.72GB |
|
37 |
+
| [llama2-7b-chat-hf-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q6_K.gguf) | Q6_K | 5.15GB |
|
38 |
+
| [llama2-7b-chat-hf-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-v3-gguf/blob/main/llama2-7b-chat-hf-v3.Q8_0.gguf) | Q8_0 | 6.67GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
The base model is meta's Llama-2-7b-chat-hf. It was finetuned using SFT and the Anthropic/hh-rlhf dataset and the model prompt is similar to the original Guanaco model.
|
45 |
+
This repo contains the merged fp16 model.
|
46 |
+
|
47 |
+
**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.**
|
48 |
+
---
|
49 |
+
- license:
|
50 |
+
- llama2 <br>
|
51 |
+
- datasets:
|
52 |
+
- Anthropic/hh-rlhf <br>
|
53 |
+
- language:
|
54 |
+
- en <br>
|
55 |
+
- reference: https://gist.github.com/younesbelkada/9f7f75c94bdc1981c8ca5cc937d4a4da
|
56 |
+
---
|
57 |
+
|