smashmaster
commited on
Commit
•
b4144ad
1
Parent(s):
df045dd
Upload folder using huggingface_hub
Browse files- README.md +26 -1
- config.json +40 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/mistral-7b-bnb-4bit
|
4 |
---
|
5 |
+
|
6 |
+
# Rosetta 0.2
|
7 |
+
|
8 |
+
|
9 |
+
## Model Details
|
10 |
+
|
11 |
+
### Model Description
|
12 |
+
|
13 |
+
Base model is the Unsloth Mistral 7b at full percision (trained on 4bit).
|
14 |
+
<!-- Provide a longer summary of what this model is. -->
|
15 |
+
|
16 |
+
|
17 |
+
|
18 |
+
- **Developed by:** smashmaster
|
19 |
+
- **Funded by:** myself
|
20 |
+
- **Model type:** Mistral 7B Finetune
|
21 |
+
- **Language(s) (NLP):** TBD
|
22 |
+
- **License:** All rights reserved (for now, def subject to change with better revisions of the model)
|
23 |
+
- **Finetuned from model:** Mistral 7B (Unsloth 4bit)
|
24 |
+
|
25 |
+
|
26 |
+
### Framework versions
|
27 |
+
|
28 |
+
- PEFT 0.7.1
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/mistral-7b",
|
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 |
+
"pad_token_id": 2,
|
19 |
+
"quantization_config": {
|
20 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
21 |
+
"bnb_4bit_quant_type": "nf4",
|
22 |
+
"bnb_4bit_use_double_quant": true,
|
23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
24 |
+
"llm_int8_has_fp16_weight": false,
|
25 |
+
"llm_int8_skip_modules": null,
|
26 |
+
"llm_int8_threshold": 6.0,
|
27 |
+
"load_in_4bit": true,
|
28 |
+
"load_in_8bit": false,
|
29 |
+
"quant_method": "bitsandbytes"
|
30 |
+
},
|
31 |
+
"rms_norm_eps": 1e-05,
|
32 |
+
"rope_theta": 10000.0,
|
33 |
+
"sliding_window": 4096,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.37.0.dev0",
|
37 |
+
"unsloth_version": "2024.1",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 32000
|
40 |
+
}
|
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 |
+
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.37.0.dev0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2d9946e65e69191d9af3829f5751a9f3cb6955348322a5a77c7fd84a28f2b75
|
3 |
+
size 4125687669
|