sharpenb commited on
Commit
16dc69c
1 Parent(s): 4b98b48

Upload folder using huggingface_hub (#2)

Browse files

- d8596285a777aa2dbfc4bf38d987ca81f5c0b397ace34e8c3ff439f5100dc8db (7d594788af80c4de6d4d112a54ed91272c64cd6d)
- 1f5274a54d6a759ff4560150a6a366d78ca7b0ff7859d56e40da12bc00c7f01c (9be89ba94015b03d95fc13b1b9b86a80798fb2d9)

Files changed (5) hide show
  1. README.md +4 -3
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. plots.png +0 -0
  5. smash_config.json +1 -1
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- library_name: pruna-engine
3
  thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
4
  metrics:
5
  - memory_disk
@@ -8,6 +7,8 @@ metrics:
8
  - inference_throughput
9
  - inference_CO2_emissions
10
  - inference_energy_consumption
 
 
11
  ---
12
  <!-- header start -->
13
  <!-- 200823 -->
@@ -33,7 +34,7 @@ metrics:
33
 
34
  ## Results
35
 
36
- Detailed efficiency metrics coming soon!
37
 
38
  **Frequently Asked Questions**
39
  - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -60,7 +61,7 @@ You can run the smashed model with these steps:
60
  from transformers import AutoModelForCausalLM, AutoTokenizer
61
 
62
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/codellama-CodeLlama-7b-Python-hf-bnb-4bit-smashed",
63
- trust_remote_code=True)
64
  tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-7b-Python-hf")
65
 
66
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
 
1
  ---
 
2
  thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
3
  metrics:
4
  - memory_disk
 
7
  - inference_throughput
8
  - inference_CO2_emissions
9
  - inference_energy_consumption
10
+ tags:
11
+ - pruna-ai
12
  ---
13
  <!-- header start -->
14
  <!-- 200823 -->
 
34
 
35
  ## Results
36
 
37
+ ![image info](./plots.png)
38
 
39
  **Frequently Asked Questions**
40
  - ***How does the compression work?*** The model is compressed with llm-int8.
 
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/codellama-CodeLlama-7b-Python-hf-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-7b-Python-hf")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/tmpv27p3nmx",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -20,7 +20,7 @@
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "bfloat16",
22
  "bnb_4bit_quant_type": "fp4",
23
- "bnb_4bit_use_double_quant": true,
24
  "llm_int8_enable_fp32_cpu_offload": false,
25
  "llm_int8_has_fp16_weight": false,
26
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmpa5njstd0",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "bfloat16",
22
  "bnb_4bit_quant_type": "fp4",
23
+ "bnb_4bit_use_double_quant": false,
24
  "llm_int8_enable_fp32_cpu_offload": false,
25
  "llm_int8_has_fp16_weight": false,
26
  "llm_int8_skip_modules": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4e1b3c91458a48f4def55031a29d5379c85993f2d4815280c7b3de64c399e9
3
- size 3866042036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491e48c081c013cd58822af07d2c7f3d53372ccba8a8a97c6a43c60798bb5606
3
+ size 4167722008
plots.png ADDED
smash_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsq4atcxpy",
12
  "batch_size": 1,
13
  "model_name": "codellama/CodeLlama-7b-Python-hf",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsrxdshhxz",
12
  "batch_size": 1,
13
  "model_name": "codellama/CodeLlama-7b-Python-hf",
14
  "pruning_ratio": 0.0,