viktorahmeti commited on
Commit
84715a4
1 Parent(s): a7aee38

Upload MistralForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -3
  2. config.json +41 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- library_name: transformers
 
3
  license: apache-2.0
 
4
  datasets:
5
  - viktorahmeti/European-Commission-Kosovo-2023-Report-QA
6
- language:
7
- - en
8
  ---
9
 
10
  # Model Card for Model ID
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
+ library_name: transformers
6
  datasets:
7
  - viktorahmeti/European-Commission-Kosovo-2023-Report-QA
 
 
8
  ---
9
 
10
  # Model Card for Model ID
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_storage": "uint8",
23
+ "bnb_4bit_quant_type": "nf4",
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": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_theta": 10000.0,
35
+ "sliding_window": 4096,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.41.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 32000
41
+ }
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": "4.41.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5873bbf93167aada3e93114a4121e7f6134ca608c25fb37341444f2dbd0996b7
3
+ size 4125687599