Commit
•
c73c7fc
1
Parent(s):
6f0fb84
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
autotrain-mixtral7x8b-math - GGUF
|
11 |
+
- Model creator: https://huggingface.co/abhishek/
|
12 |
+
- Original model: https://huggingface.co/abhishek/autotrain-mixtral7x8b-math/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [autotrain-mixtral7x8b-math.Q2_K.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q2_K.gguf) | Q2_K | 16.12GB |
|
18 |
+
| [autotrain-mixtral7x8b-math.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.IQ3_XS.gguf) | IQ3_XS | 18.02GB |
|
19 |
+
| [autotrain-mixtral7x8b-math.IQ3_S.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.IQ3_S.gguf) | IQ3_S | 19.03GB |
|
20 |
+
| [autotrain-mixtral7x8b-math.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q3_K_S.gguf) | Q3_K_S | 19.03GB |
|
21 |
+
| [autotrain-mixtral7x8b-math.IQ3_M.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.IQ3_M.gguf) | IQ3_M | 19.96GB |
|
22 |
+
| [autotrain-mixtral7x8b-math.Q3_K.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q3_K.gguf) | Q3_K | 21.0GB |
|
23 |
+
| [autotrain-mixtral7x8b-math.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q3_K_M.gguf) | Q3_K_M | 21.0GB |
|
24 |
+
| [autotrain-mixtral7x8b-math.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q3_K_L.gguf) | Q3_K_L | 22.51GB |
|
25 |
+
| [autotrain-mixtral7x8b-math.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.IQ4_XS.gguf) | IQ4_XS | 23.63GB |
|
26 |
+
| [autotrain-mixtral7x8b-math.Q4_0.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q4_0.gguf) | Q4_0 | 24.63GB |
|
27 |
+
| [autotrain-mixtral7x8b-math.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.IQ4_NL.gguf) | IQ4_NL | 24.91GB |
|
28 |
+
| [autotrain-mixtral7x8b-math.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q4_K_S.gguf) | Q4_K_S | 24.91GB |
|
29 |
+
| [autotrain-mixtral7x8b-math.Q4_K.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q4_K.gguf) | Q4_K | 26.49GB |
|
30 |
+
| [autotrain-mixtral7x8b-math.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q4_K_M.gguf) | Q4_K_M | 26.49GB |
|
31 |
+
| [autotrain-mixtral7x8b-math.Q4_1.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q4_1.gguf) | Q4_1 | 27.32GB |
|
32 |
+
| [autotrain-mixtral7x8b-math.Q5_0.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q5_0.gguf) | Q5_0 | 30.02GB |
|
33 |
+
| [autotrain-mixtral7x8b-math.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q5_K_S.gguf) | Q5_K_S | 30.02GB |
|
34 |
+
| [autotrain-mixtral7x8b-math.Q5_K.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q5_K.gguf) | Q5_K | 30.95GB |
|
35 |
+
| [autotrain-mixtral7x8b-math.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q5_K_M.gguf) | Q5_K_M | 30.95GB |
|
36 |
+
| [autotrain-mixtral7x8b-math.Q5_1.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q5_1.gguf) | Q5_1 | 32.71GB |
|
37 |
+
| [autotrain-mixtral7x8b-math.Q6_K.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/blob/main/autotrain-mixtral7x8b-math.Q6_K.gguf) | Q6_K | 35.74GB |
|
38 |
+
| [autotrain-mixtral7x8b-math.Q8_0.gguf](https://huggingface.co/RichardErkhov/abhishek_-_autotrain-mixtral7x8b-math-gguf/tree/main/) | Q8_0 | 46.22GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
---
|
45 |
+
tags:
|
46 |
+
- autotrain
|
47 |
+
- text-generation-inference
|
48 |
+
- text-generation
|
49 |
+
library_name: transformers
|
50 |
+
widget:
|
51 |
+
- messages:
|
52 |
+
- role: user
|
53 |
+
content: What is your favorite condiment?
|
54 |
+
license: other
|
55 |
+
---
|
56 |
+
|
57 |
+
# Model Trained Using AutoTrain
|
58 |
+
|
59 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
60 |
+
|
61 |
+
# Usage
|
62 |
+
|
63 |
+
```python
|
64 |
+
|
65 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
66 |
+
|
67 |
+
model_path = "PATH_TO_THIS_REPO"
|
68 |
+
|
69 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
70 |
+
model = AutoModelForCausalLM.from_pretrained(
|
71 |
+
model_path,
|
72 |
+
device_map="auto",
|
73 |
+
torch_dtype='auto'
|
74 |
+
).eval()
|
75 |
+
|
76 |
+
# Prompt content: "hi"
|
77 |
+
messages = [
|
78 |
+
{"role": "user", "content": "hi"}
|
79 |
+
]
|
80 |
+
|
81 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
82 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
83 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
84 |
+
|
85 |
+
# Model response: "Hello! How can I assist you today?"
|
86 |
+
print(response)
|
87 |
+
```
|
88 |
+
|