rejauldu commited on
Commit
c8cf630
1 Parent(s): 250124f

Upload MistralForCausalLM

Browse files
README.md CHANGED
@@ -6,6 +6,8 @@ license: apache-2.0
6
  tags:
7
  - finetuned
8
  - bengali
 
 
9
  datasets:
10
  - iamshnoo/alpaca-cleaned-bengali
11
  pipeline_tag: text-generation
 
6
  tags:
7
  - finetuned
8
  - bengali
9
+ - trl
10
+ - sft
11
  datasets:
12
  - iamshnoo/alpaca-cleaned-bengali
13
  pipeline_tag: text-generation
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-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
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "_load_in_4bit": true,
21
+ "_load_in_8bit": false,
22
+ "bnb_4bit_compute_dtype": "bfloat16",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_theta": 10000.0,
36
+ "sliding_window": 4096,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.41.1",
40
+ "use_cache": false,
41
+ "vocab_size": 32000
42
+ }
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": "4.41.1"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ea9c17c6f1ad4b56f3f998a0ed2ec7984a07bd07da5b7c0e065836c73f8b4d
3
+ size 4997692569
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087086c1694bd1db2960f37250a512549775659ff625dd5ecfc24430ccf3cdf9
3
+ size 658362607
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff