sharpenb commited on
Commit
2f11625
1 Parent(s): f1dcbef

Upload folder using huggingface_hub (#2)

Browse files

- 96f101b6bcf78ce8dd4cccc2b13b4e8aff4289cfc24b3f03c616b287a3c61e8b (0ff7b3deafd926912c41944eeb0f384db740a4e0)
- 87ee6e095520edbde2f4291883f135dc76bb3cfc1ca91bdb55f25b9a2135c552 (8fa9f1923d50566302e96fba85cb5b5d774b9b79)

Files changed (4) hide show
  1. README.md +4 -3
  2. config.json +2 -2
  3. plots.png +0 -0
  4. 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/togethercomputer-GPT-JT-6B-v1-bnb-8bit-smashed",
63
- trust_remote_code=True)
64
  tokenizer = AutoTokenizer.from_pretrained("togethercomputer/GPT-JT-6B-v1")
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/togethercomputer-GPT-JT-6B-v1-bnb-8bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("togethercomputer/GPT-JT-6B-v1")
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/tmpkljysk8l",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPTJForCausalLM"
@@ -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/tmpeni0rokz",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPTJForCausalLM"
 
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": [
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/modelsrazqgkn6",
12
  "batch_size": 1,
13
  "model_name": "togethercomputer/GPT-JT-6B-v1",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelssela5xxd",
12
  "batch_size": 1,
13
  "model_name": "togethercomputer/GPT-JT-6B-v1",
14
  "pruning_ratio": 0.0,