sharpenb commited on
Commit
f59ab84
1 Parent(s): 74d8066

Upload folder using huggingface_hub (#2)

Browse files

- 5db4c0ac4a5724ee05593fb19bf95428b7a3dec3e6727271bdbea8f5f8961252 (01b57b9c1adc2cf0f034eed02bb950d8e3749e77)
- 4001bf82a8ec56cdcdecd8c8db7c8ca8ea0ab99f090838d1761a2a91fbe23f39 (dbfe944ffc3ee9a01f02f1e50c70a5f0af9ef75e)

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/TinyPixel-Llama-2-7B-bf16-sharded-bnb-8bit-smashed",
63
- trust_remote_code=True)
64
  tokenizer = AutoTokenizer.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded")
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/TinyPixel-Llama-2-7B-bf16-sharded-bnb-8bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded")
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/tmp_d2n15_z",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -21,7 +21,7 @@
21
  "quantization_config": {
22
  "bnb_4bit_compute_dtype": "bfloat16",
23
  "bnb_4bit_quant_type": "fp4",
24
- "bnb_4bit_use_double_quant": true,
25
  "llm_int8_enable_fp32_cpu_offload": false,
26
  "llm_int8_has_fp16_weight": false,
27
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmpmsdupfy0",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
21
  "quantization_config": {
22
  "bnb_4bit_compute_dtype": "bfloat16",
23
  "bnb_4bit_quant_type": "fp4",
24
+ "bnb_4bit_use_double_quant": false,
25
  "llm_int8_enable_fp32_cpu_offload": false,
26
  "llm_int8_has_fp16_weight": false,
27
  "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/modelsvc_l2yck",
12
  "batch_size": 1,
13
  "model_name": "TinyPixel/Llama-2-7B-bf16-sharded",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsrs345xt2",
12
  "batch_size": 1,
13
  "model_name": "TinyPixel/Llama-2-7B-bf16-sharded",
14
  "pruning_ratio": 0.0,