Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +1 -0
- config.json +56 -0
- generation_config.json +14 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
- unsloth
|
| 7 |
- gemma3_text
|
| 8 |
- trl
|
|
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
|
|
|
| 6 |
- unsloth
|
| 7 |
- gemma3_text
|
| 8 |
- trl
|
| 9 |
+
- sft
|
| 10 |
license: apache-2.0
|
| 11 |
language:
|
| 12 |
- en
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"eos_token_id": 106,
|
| 11 |
+
"final_logit_softcapping": null,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 14 |
+
"hidden_size": 640,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 2048,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"sliding_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention"
|
| 36 |
+
],
|
| 37 |
+
"max_position_embeddings": 32768,
|
| 38 |
+
"model_type": "gemma3_text",
|
| 39 |
+
"num_attention_heads": 4,
|
| 40 |
+
"num_hidden_layers": 18,
|
| 41 |
+
"num_key_value_heads": 1,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"query_pre_attn_scalar": 256,
|
| 44 |
+
"rms_norm_eps": 1e-06,
|
| 45 |
+
"rope_local_base_freq": 10000.0,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 1000000.0,
|
| 48 |
+
"sliding_window": 512,
|
| 49 |
+
"torch_dtype": "float16",
|
| 50 |
+
"transformers_version": "4.55.2",
|
| 51 |
+
"unsloth_fixed": true,
|
| 52 |
+
"unsloth_version": "2025.8.9",
|
| 53 |
+
"use_bidirectional_attention": false,
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 262144
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"max_length": 32768,
|
| 10 |
+
"pad_token_id": 0,
|
| 11 |
+
"top_k": 64,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "4.55.2"
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc709f6be9a34d4ea59379b2bce1c473dc8afd8af574a4952ce625c6589bf12
|
| 3 |
+
size 551554368
|