Hugging Face's logo

cmarkea
/
CodeLlama-34b-Instruct-hf-4bit

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Cyrile commited on
Commit
c959aec
•
1 Parent(s): 79cf9ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -16,20 +16,20 @@ for the task, to 5, representing a model that fully met expectations. The evalua
16
  Java, JavaScript, and Pseudo-code. All tests were conducted in a French-language context, and models were heavily penalized if they responded in another language,
17
  even if the response was technically correct.
18
 
19
- | model | score | # params (Billion) | size (GB) |
20
- |------------------------------------------------:|:-----------:|:------------------:|:---------:|
21
- | gemini-1.5-pro | 4.50995 | NA | NA |
22
- | gpt-4o | 4.50995 | NA | NA |
23
- | claude3.5-sonnet | 4.48756 | NA | NA |
24
- | deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | 4.23691 | 15.7 | 31.4 |
25
- | meta-llama/Meta-Llama-3.1-70B-Instruct | 4.23383 | 70.06 | 140.12 |
26
- | cmarkea/Meta-Llama-3.1-70B-Instruct-4bit | 4.1393 | 70.06 | 35.3 |
27
- | cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit | 3.801 | 46.7 | 23.35 |
28
- | meta-llama/Meta-Llama-3.1-8B-Instruct | 3.72637 | 8.03 | 16.06 |
29
- | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.33416 | 46.7 | 93.4 |
30
- | codellama/CodeLlama-13b-Instruct-hf | 3.32836 | 13 | 26 |
31
- | codellama/CodeLlama-34b-Instruct-hf | 3.27363 | 33.7 | 67.4 |
32
- | codellama/CodeLlama-7b-Instruct-hf | 3.19403 | 6.74 | 13.48 |
33
- | **cmarkea/CodeLlama-34b-Instruct-hf-4bit** | **3.12189** | **33.7** | **16.85** |
34
- | codellama/CodeLlama-70b-Instruct-hf | 1.81592 | 69 | 138 |
35
- | cmarkea/CodeLlama-70b-Instruct-hf-4bit | 1.6409 | 69 | 34.5 |
 
16
  Java, JavaScript, and Pseudo-code. All tests were conducted in a French-language context, and models were heavily penalized if they responded in another language,
17
  even if the response was technically correct.
18
 
19
+ | model | score | # params (Billion) | size (GB) |
20
+ |------------------------------------------------:|:--------:|:------------------:|:---------:|
21
+ | gemini-1.5-pro | 4.51 | NA | NA |
22
+ | gpt-4o | 4.51 | NA | NA |
23
+ | claude3.5-sonnet | 4.49 | NA | NA |
24
+ | deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | 4.24 | 15.7 | 31.4 |
25
+ | meta-llama/Meta-Llama-3.1-70B-Instruct | 4.23 | 70.06 | 140.12 |
26
+ | cmarkea/Meta-Llama-3.1-70B-Instruct-4bit | 4.14 | 70.06 | 35.3 |
27
+ | cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit | 3.8 | 46.7 | 23.35 |
28
+ | meta-llama/Meta-Llama-3.1-8B-Instruct | 3.73 | 8.03 | 16.06 |
29
+ | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.33 | 46.7 | 93.4 |
30
+ | codellama/CodeLlama-13b-Instruct-hf | 3.33 | 13 | 26 |
31
+ | codellama/CodeLlama-34b-Instruct-hf | 3.27 | 33.7 | 67.4 |
32
+ | codellama/CodeLlama-7b-Instruct-hf | 3.19 | 6.74 | 13.48 |
33
+ | **cmarkea/CodeLlama-34b-Instruct-hf-4bit** | **3.12** | **33.7** | **16.85** |
34
+ | codellama/CodeLlama-70b-Instruct-hf | 1.82 | 69 | 138 |
35
+ | cmarkea/CodeLlama-70b-Instruct-hf-4bit | 1.64 | 69 | 34.5 |