Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| cvx-coder.Q2_K.gguf | Q2_K | 1.32GB |
| cvx-coder.IQ3_XS.gguf | IQ3_XS | 1.51GB |
| cvx-coder.IQ3_S.gguf | IQ3_S | 1.57GB |
| cvx-coder.Q3_K_S.gguf | Q3_K_S | 1.57GB |
| cvx-coder.IQ3_M.gguf | IQ3_M | 1.73GB |
| cvx-coder.Q3_K.gguf | Q3_K | 1.82GB |
| cvx-coder.Q3_K_M.gguf | Q3_K_M | 1.82GB |
| cvx-coder.Q3_K_L.gguf | Q3_K_L | 1.94GB |
| cvx-coder.IQ4_XS.gguf | IQ4_XS | 1.93GB |
| cvx-coder.Q4_0.gguf | Q4_0 | 2.03GB |
| cvx-coder.IQ4_NL.gguf | IQ4_NL | 2.04GB |
| cvx-coder.Q4_K_S.gguf | Q4_K_S | 2.04GB |
| cvx-coder.Q4_K.gguf | Q4_K | 2.23GB |
| cvx-coder.Q4_K_M.gguf | Q4_K_M | 2.23GB |
| cvx-coder.Q4_1.gguf | Q4_1 | 2.24GB |
| cvx-coder.Q5_0.gguf | Q5_0 | 2.46GB |
| cvx-coder.Q5_K_S.gguf | Q5_K_S | 2.46GB |
| cvx-coder.Q5_K.gguf | Q5_K | 2.62GB |
| cvx-coder.Q5_K_M.gguf | Q5_K_M | 2.62GB |
| cvx-coder.Q5_1.gguf | Q5_1 | 2.68GB |
| cvx-coder.Q6_K.gguf | Q6_K | 2.92GB |
| cvx-coder.Q8_0.gguf | Q8_0 | 3.78GB |
1from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
2m_path="tim1900/cvx-coder"
3model = AutoModelForCausalLM.from_pretrained(
4 m_path,
5 device_map="auto",
6 torch_dtype="auto",
7 trust_remote_code=True,
8)
9tokenizer = AutoTokenizer.from_pretrained(m_path)
10pipe = pipeline(
11 "text-generation",
12 model=model,
13 tokenizer=tokenizer,
14)
15generation_args = {
16 "max_new_tokens": 2000,
17 "return_full_text": False,
18 "temperature": 0,
19 "do_sample": False,
20}
21content='''my problem is not convex, can i use cvx? if not, what should i do, be specific.'''
22messages = [
23 {"role": "user", "content": content},
24]
25output = pipe(messages, **generation_args)
26print(output[0]['generated_text'])1import gradio as gr
2from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
3m_path="tim1900/cvx-coder"
4model = AutoModelForCausalLM.from_pretrained(
5 m_path,
6 device_map="auto",
7 torch_dtype="auto",
8 trust_remote_code=True,
9)
10tokenizer = AutoTokenizer.from_pretrained(m_path)
11pipe = pipeline(
12 "text-generation",
13 model=model,
14 tokenizer=tokenizer,
15)
16generation_args = {
17 "max_new_tokens": 2000,
18 "return_full_text": False,
19 "temperature": 0,
20 "do_sample": False,
21}
22
23def assistant_talk(message, history):
24 message=[
25 {"role": "user", "content": message},
26 ]
27 temp=[]
28 for i in history:
29 temp+=[{"role": "user", "content": i[0]},{"role": "assistant", "content": i[1]}]
30
31 messages =temp + message
32
33 output = pipe(messages, **generation_args)
34 return output[0]['generated_text']
35gr.ChatInterface(assistant_talk).launch()