Hugging Face's logo

intelpen
/
OpenLLM-Ro-RoLLama2-7b-Instruct-v1-4Bit-BB

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
intelpen commited on
Commit
fef9b34
•
1 Parent(s): e1669b7

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/adapter_config.json +0 -0
  3. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/added_tokens.json +0 -0
  4. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/special_tokens_map.json +0 -0
  5. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer.json +0 -0
  6. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer.model +0 -0
  7. .no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer_config.json +0 -0
  8. blobs/05283793bb9bb2f7a016ed90b7bedee58adbea84 +6 -0
  9. blobs/574472aa10ae61f5d983e5acb487937d70929e9a +43 -0
  10. blobs/703ba87ce335ea359e7e4f47aaf51a1ba4b2d29f93a008bab1c8be0068228e7e +3 -0
  11. refs/main +1 -0
  12. snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/config.json +43 -0
  13. snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/generation_config.json +6 -0
  14. snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ blobs/703ba87ce335ea359e7e4f47aaf51a1ba4b2d29f93a008bab1c8be0068228e7e filter=lfs diff=lfs merge=lfs -text
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/adapter_config.json ADDED
File without changes
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/added_tokens.json ADDED
File without changes
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/special_tokens_map.json ADDED
File without changes
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer.json ADDED
File without changes
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer.model ADDED
File without changes
.no_exist/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/tokenizer_config.json ADDED
File without changes
blobs/05283793bb9bb2f7a016ed90b7bedee58adbea84 ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
blobs/574472aa10ae61f5d983e5acb487937d70929e9a ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OpenLLM-Ro/RoLlama2-7b-Instruct-v1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.40.0.dev0",
41
+ "use_cache": true,
42
+ "vocab_size": 32004
43
+ }
blobs/703ba87ce335ea359e7e4f47aaf51a1ba4b2d29f93a008bab1c8be0068228e7e ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703ba87ce335ea359e7e4f47aaf51a1ba4b2d29f93a008bab1c8be0068228e7e
3
+ size 3866107634
refs/main ADDED
@@ -0,0 +1 @@
 
 
1
+ e1669b7dc3b8b6d52666fe1f936628e69b4a8b81
snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OpenLLM-Ro/RoLlama2-7b-Instruct-v1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.40.0.dev0",
41
+ "use_cache": true,
42
+ "vocab_size": 32004
43
+ }
snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
snapshots/e1669b7dc3b8b6d52666fe1f936628e69b4a8b81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703ba87ce335ea359e7e4f47aaf51a1ba4b2d29f93a008bab1c8be0068228e7e
3
+ size 3866107634