alnrg2arg commited on
Commit
ca4a853
·
verified ·
1 Parent(s): 58c3c23

Upload MistralForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alnrg2arg/blockchainlabs_7B_merged_test2_4_prune",
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
+ "bnb_4bit_compute_dtype": "bfloat16",
20
+ "bnb_4bit_quant_type": "nf4",
21
+ "bnb_4bit_use_double_quant": true,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": "null",
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": true,
27
+ "load_in_8bit": false,
28
+ "quant_method": "bitsandbytes"
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_theta": 10000.0,
32
+ "sliding_window": 4096,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.37.0",
36
+ "unsloth_version": "2024.1",
37
+ "use_cache": false,
38
+ "vocab_size": 32000
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0",
6
+ "use_cache": false
7
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dabbee63af11bf967bdcd7e5e7021632de6461470b66505a3cc9606cf6ad672
3
+ size 4810124586
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf74c8c46c8315d7050752a58ab9d50623e09f9440ec7d4f7993dad9632e5f3
3
+ size 4851164435
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebdb6790b9681d89a21e9853b2cbeaa9c668c2c982f8a76d130354e76303f0f
3
+ size 4783812213
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0f47f4393af788b752eff1171df68397d3f6dd9233092faf1b1e54b24246d2
3
+ size 4851164656
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf655afe9a2bf8961edded68a4a835f261a74f11600e22ebbb33a55e5b82621
3
+ size 4783812220
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d49edc5ba225877336cf5a1e1ed1bc713467037c24b20101943ff324b72bb5
3
+ size 4473241516
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff