Total runs:
64.8K
Run Growth:
63.9K
Growth Rate:
98.62%
Sponsored by
APIMaster
solidrust / Llama-3-8B-Instruct-Coder-AWQ
Model's Last Updated: September 03 2024
text-generation
Introduction of Llama-3-8B-Instruct-Coder-AWQ
Model Details of Llama-3-8B-Instruct-Coder-AWQ
rombodawg/Llama-3-8B-Instruct-Coder AWQ
- Model creator: rombodawg
- Original model: Llama-3-8B-Instruct-Coder
Model Summary
This model is llama-3-8b-instruct from Meta (uploaded by unsloth) trained on the full 65k Codefeedback dataset + the additional 150k Code Feedback Filtered Instruction dataset combined. You can find that dataset linked below. This AI model was trained with the new Qalore method developed by my good friend on Discord and fellow Replete-AI worker walmartbag.
The Qalore method uses Qlora training along with the methods from Galore for additional reductions in VRAM allowing for llama-3-8b to be loaded on 14.5 GB of VRAM. This allowed this training to be completed on an RTX A4000 16GB in 130 hours for less than $20.
How to use
Install the necessary packages
pip install --upgrade autoawq autoawq-kernels
Example Python code
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Llama-3-8B-Instruct-Coder-AWQ"
system_message = "You are Llama-3-8B-Instruct-Coder, incarnated as a powerful AI. You were created by rombodawg."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- Text Generation Webui - using Loader: AutoAWQ
- vLLM - version 0.2.2 or later for support for all model types.
- Hugging Face Text Generation Inference (TGI)
- Transformers version 4.35.0 and later, from any code or client that supports Transformers
- AutoAWQ - for use from Python code
Runs of solidrust Llama-3-8B-Instruct-Coder-AWQ on huggingface.co
27
Total runs
-1
24-hour runs
0
3-day runs
4
7-day runs
12
30-day runs
More Information About Llama-3-8B-Instruct-Coder-AWQ huggingface.co Model
Url of Llama-3-8B-Instruct-Coder-AWQ
Llama-3-8B-Instruct-Coder-AWQ huggingface.co Url
Provider of Llama-3-8B-Instruct-Coder-AWQ huggingface.co
Other API from solidrust
Updated:September 03 2024
Total runs:
42.6K
Run Growth:
29.0K
Growth Rate:
81.77%
Total runs:
32.7K
Run Growth:
-396.9K
Growth Rate:
-999.99%
Total runs:
1.6K
Run Growth:
126
Growth Rate:
8.05%
Total runs:
530
Run Growth:
327
Growth Rate:
61.81%
Total runs:
448
Run Growth:
161
Growth Rate:
35.94%
Total runs:
343
Run Growth:
-439
Growth Rate:
-126.51%
Total runs:
338
Run Growth:
-4.0K
Growth Rate:
-1148.55%
Total runs:
316
Run Growth:
250
Growth Rate:
77.40%
Total runs:
311
Run Growth:
-116
Growth Rate:
-37.06%
Total runs:
258
Run Growth:
-140
Growth Rate:
-53.64%
Total runs:
230
Run Growth:
-67
Growth Rate:
-29.26%
Total runs:
197
Run Growth:
-43
Growth Rate:
-21.83%
Total runs:
168
Run Growth:
0
Growth Rate:
0.00%
Total runs:
168
Run Growth:
0
Growth Rate:
0.00%
Total runs:
105
Run Growth:
-132
Growth Rate:
-113.79%
Total runs:
98
Run Growth:
16
Growth Rate:
16.33%
Total runs:
98
Run Growth:
-234
Growth Rate:
-234.00%
Total runs:
89
Run Growth:
-176
Growth Rate:
-197.75%
Total runs:
86
Run Growth:
-57
Growth Rate:
-66.28%
Total runs:
80
Run Growth:
-350
Growth Rate:
-443.04%
Total runs:
66
Run Growth:
52
Growth Rate:
78.79%
Total runs:
63
Run Growth:
-24
Growth Rate:
-37.50%
Total runs:
54
Run Growth:
43
Growth Rate:
79.63%
Total runs:
53
Run Growth:
-33
Growth Rate:
-62.26%
Total runs:
46
Run Growth:
-44
Growth Rate:
-95.65%
Total runs:
45
Run Growth:
-37
Growth Rate:
-80.43%
Total runs:
40
Run Growth:
-38
Growth Rate:
-90.48%
Total runs:
37
Run Growth:
19
Growth Rate:
52.78%
Total runs:
34
Run Growth:
-8
Growth Rate:
-22.86%
Total runs:
34
Run Growth:
1
Growth Rate:
3.03%
Total runs:
34
Run Growth:
-13
Growth Rate:
-38.24%
Total runs:
32
Run Growth:
19
Growth Rate:
57.58%
Total runs:
32
Run Growth:
22
Growth Rate:
66.67%
Total runs:
31
Run Growth:
19
Growth Rate:
67.86%
Total runs:
30
Run Growth:
21
Growth Rate:
67.74%
Total runs:
30
Run Growth:
10
Growth Rate:
34.48%
Total runs:
30
Run Growth:
13
Growth Rate:
41.94%
Total runs:
29
Run Growth:
16
Growth Rate:
64.00%
Total runs:
29
Run Growth:
11
Growth Rate:
37.93%
Total runs:
29
Run Growth:
2
Growth Rate:
7.41%
Total runs:
29
Run Growth:
3
Growth Rate:
10.34%
Total runs:
29
Run Growth:
-8
Growth Rate:
-26.67%
Total runs:
28
Run Growth:
3
Growth Rate:
11.54%
Total runs:
28
Run Growth:
18
Growth Rate:
64.29%
Total runs:
27
Run Growth:
19
Growth Rate:
73.08%
Total runs:
27
Run Growth:
15
Growth Rate:
57.69%
Total runs:
27
Run Growth:
10
Growth Rate:
40.00%
Total runs:
27
Run Growth:
15
Growth Rate:
53.57%
Total runs:
26
Run Growth:
16
Growth Rate:
64.00%
Total runs:
26
Run Growth:
14
Growth Rate:
56.00%
Total runs:
26
Run Growth:
8
Growth Rate:
32.00%
Total runs:
25
Run Growth:
11
Growth Rate:
45.83%
Total runs:
25
Run Growth:
12
Growth Rate:
48.00%
Total runs:
25
Run Growth:
11
Growth Rate:
45.83%
Total runs:
25
Run Growth:
9
Growth Rate:
36.00%
Total runs:
24
Run Growth:
10
Growth Rate:
41.67%
Total runs:
24
Run Growth:
11
Growth Rate:
47.83%
Total runs:
24
Run Growth:
12
Growth Rate:
50.00%
Total runs:
24
Run Growth:
13
Growth Rate:
54.17%
Total runs:
24
Run Growth:
13
Growth Rate:
54.17%
Total runs:
24
Run Growth:
8
Growth Rate:
36.36%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
24
Run Growth:
12
Growth Rate:
50.00%
Total runs:
24
Run Growth:
10
Growth Rate:
45.45%
Total runs:
23
Run Growth:
10
Growth Rate:
45.45%
Total runs:
23
Run Growth:
9
Growth Rate:
39.13%
Total runs:
23
Run Growth:
12
Growth Rate:
52.17%
Total runs:
23
Run Growth:
9
Growth Rate:
42.86%
Total runs:
23
Run Growth:
15
Growth Rate:
65.22%
Total runs:
23
Run Growth:
10
Growth Rate:
43.48%
Total runs:
23
Run Growth:
11
Growth Rate:
50.00%
Total runs:
23
Run Growth:
15
Growth Rate:
65.22%
Total runs:
23
Run Growth:
14
Growth Rate:
60.87%
Total runs:
23
Run Growth:
5
Growth Rate:
23.81%
Total runs:
23
Run Growth:
7
Growth Rate:
30.43%
Total runs:
23
Run Growth:
8
Growth Rate:
34.78%
Total runs:
23
Run Growth:
11
Growth Rate:
47.83%
Total runs:
22
Run Growth:
-1
Growth Rate:
-5.26%
Total runs:
22
Run Growth:
10
Growth Rate:
47.62%
Total runs:
22
Run Growth:
15
Growth Rate:
62.50%
Total runs:
22
Run Growth:
7
Growth Rate:
33.33%
Total runs:
22
Run Growth:
3
Growth Rate:
14.29%
Total runs:
22
Run Growth:
11
Growth Rate:
52.38%
Total runs:
22
Run Growth:
11
Growth Rate:
50.00%
Total runs:
22
Run Growth:
10
Growth Rate:
45.45%
Total runs:
22
Run Growth:
-3
Growth Rate:
-13.64%
Total runs:
22
Run Growth:
7
Growth Rate:
33.33%
Total runs:
22
Run Growth:
12
Growth Rate:
57.14%
Total runs:
22
Run Growth:
16
Growth Rate:
64.00%
Total runs:
22
Run Growth:
6
Growth Rate:
25.00%
Total runs:
21
Run Growth:
5
Growth Rate:
26.32%
Total runs:
21
Run Growth:
9
Growth Rate:
45.00%
Total runs:
21
Run Growth:
12
Growth Rate:
57.14%
Total runs:
21
Run Growth:
9
Growth Rate:
50.00%
Total runs:
21
Run Growth:
8
Growth Rate:
38.10%