Commit
•
6dad5a2
1
Parent(s):
1ba0e1f
Trained with Unsloth
Browse files- README.md +1 -28
- config.json +31 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -9,34 +9,7 @@ tags:
|
|
| 9 |
- unsloth
|
| 10 |
- llama
|
| 11 |
- trl
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
Before:
|
| 15 |
-
কম্পিউটাৰ এন্ড এন্ডিং এন্ডিং এন্ডিং �
|
| 16 |
-
কম্পিউটাৰ এন্ড এন্ডিং এন্ডিং এন্ডিং �
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
After:
|
| 20 |
-
কম্পিউটাৰ সংবাদ এই সমূহ এই সংবাদ এই সমূ
|
| 21 |
-
কম্পিউটাৰ সংবাদ এই সমূহ এই সংবাদ এই সমূ
|
| 22 |
-
|
| 23 |
-
```
|
| 24 |
-
max_seq_length = 1024
|
| 25 |
-
per_device_train_batch_size = 2,
|
| 26 |
-
gradient_accumulation_steps = 4,
|
| 27 |
-
warmup_steps = 2,
|
| 28 |
-
max_steps = 10,
|
| 29 |
-
learning_rate = 0.0005,
|
| 30 |
-
fp16 = not torch.cuda.is_bf16_supported(),
|
| 31 |
-
bf16 = torch.cuda.is_bf16_supported(),
|
| 32 |
-
logging_steps = 1,
|
| 33 |
-
optim = "adamw_8bit",
|
| 34 |
-
weight_decay = 0.01,
|
| 35 |
-
lr_scheduler_type = "linear",
|
| 36 |
-
seed = 3407,
|
| 37 |
-
output_dir = "outputs",
|
| 38 |
-
```
|
| 39 |
-
|
| 40 |
---
|
| 41 |
|
| 42 |
# Uploaded model
|
|
|
|
| 9 |
- unsloth
|
| 10 |
- llama
|
| 11 |
- trl
|
| 12 |
+
- sft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# Uploaded model
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "unsloth/tinyllama-bnb-4bit",
|
| 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": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float16",
|
| 27 |
+
"transformers_version": "4.41.2",
|
| 28 |
+
"unsloth_version": "2024.6",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32000
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94035f6793eaaebc2e19bda71fbb783ae4f713ead66d35a5071aa5c6b4e3552a
|
| 3 |
+
size 2200119664
|