Hugging Face's logo

abhishek3jangid
/
llama_31_70b_quantized_pruned_10_perc_unstructured

Safetensors
llama
8-bit precision
bitsandbytes
Model card Files Community
abhishek3jangid commited on
Commit
88d9979
·
verified ·
1 Parent(s): e90389f

Initial upload

Browse files
Files changed (18) hide show
  1. config.json +55 -0
  2. generation_config.json +12 -0
  3. model-00001-of-00015.safetensors +3 -0
  4. model-00002-of-00015.safetensors +3 -0
  5. model-00003-of-00015.safetensors +3 -0
  6. model-00004-of-00015.safetensors +3 -0
  7. model-00005-of-00015.safetensors +3 -0
  8. model-00006-of-00015.safetensors +3 -0
  9. model-00007-of-00015.safetensors +3 -0
  10. model-00008-of-00015.safetensors +3 -0
  11. model-00009-of-00015.safetensors +3 -0
  12. model-00010-of-00015.safetensors +3 -0
  13. model-00011-of-00015.safetensors +3 -0
  14. model-00012-of-00015.safetensors +3 -0
  15. model-00013-of-00015.safetensors +3 -0
  16. model-00014-of-00015.safetensors +3 -0
  17. model-00015-of-00015.safetensors +3 -0
  18. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "abhishek3jangid/llama_31_70b_pruned_5_perc_unstructured",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 80,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "quantization_config": {
27
+ "_load_in_4bit": false,
28
+ "_load_in_8bit": true,
29
+ "bnb_4bit_compute_dtype": "float32",
30
+ "bnb_4bit_quant_storage": "uint8",
31
+ "bnb_4bit_quant_type": "fp4",
32
+ "bnb_4bit_use_double_quant": false,
33
+ "llm_int8_enable_fp32_cpu_offload": false,
34
+ "llm_int8_has_fp16_weight": false,
35
+ "llm_int8_skip_modules": null,
36
+ "llm_int8_threshold": 6.0,
37
+ "load_in_4bit": false,
38
+ "load_in_8bit": true,
39
+ "quant_method": "bitsandbytes"
40
+ },
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": {
43
+ "factor": 8.0,
44
+ "high_freq_factor": 4.0,
45
+ "low_freq_factor": 1.0,
46
+ "original_max_position_embeddings": 8192,
47
+ "rope_type": "llama3"
48
+ },
49
+ "rope_theta": 500000.0,
50
+ "tie_word_embeddings": false,
51
+ "torch_dtype": "float16",
52
+ "transformers_version": "4.47.0",
53
+ "use_cache": false,
54
+ "vocab_size": 128256
55
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.47.0"
12
+ }
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ab19457388449116b7b959fe3b9942d22689f03cd82d35f35909897c4ec5b4
3
+ size 4820443921
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb351ddf65cccfacfd0929e907038b976032b4b7b86655cc2ee253afcda2aa6
3
+ size 4984984966
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7e113694ac5aaa5605a2df7b0eddf3640d8ef2d3555bef99eca03a454b0416
3
+ size 4901107961
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a22d14ba076da098f3519bde47bfd1102edb00c4f3a35c8897bdc4d8fec26c
3
+ size 4901059057
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b03c2848371dae99023ed566ee3b7fb5c6dceb99992a7700e438390b8fd6b95
3
+ size 4901059057
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1debd65bc6b47e9a1a5103ea03480dc49e6f5c7c16e02e53245966861cdc70
3
+ size 4984985094
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82b0861927dfb8246a9499b322f42e62927431a384163fd5c1985fc8734420f
3
+ size 4901107985
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fa93af14afd2697d2253f29fa63351ec1e85307a922e03376b5b91f0b710d4
3
+ size 4901059057
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4568950e14b59de4809af8ddc587e489b49b7cd148e524c3c6d45dbbcb58a05
3
+ size 4901059057
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b58ca4bd6059620f56e895d34bb51c2d82c3c0855ffaa772a6b8222a165e367
3
+ size 4984985094
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13642a630d4d7b28ba5df4205406272d10884d4dad0ecc179d7790cf48473c75
3
+ size 4901107985
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8171d2872494fa3073a800e5ebd625422713b41449d57053704e135b7fdd6577
3
+ size 4901059057
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f48edf90c89a74e846f3c62db5fcd57bb534940c74b52cad7a426e78df3b20
3
+ size 4901059057
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd666f200e6b1fc09b4996655cff47bfbd9312867ae954011fd70ad4ed2c7cb
3
+ size 4984985094
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c6a63610cfacad9173604f091e6a665abe25b2a53cd9a1a7730e239c72d8d4
3
+ size 3813381270
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff