Trained with Unsloth
Browse files- README.md +4 -1
- config.json +6 -19
- generation_config.json +2 -1
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
tags:
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- unsloth
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for Model ID
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gemma-2-9b-
|
| 3 |
"architectures": [
|
| 4 |
"Gemma2ForCausalLM"
|
| 5 |
],
|
|
@@ -22,28 +22,15 @@
|
|
| 22 |
"num_hidden_layers": 42,
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
-
"quantization_config": {
|
| 26 |
-
"_load_in_4bit": false,
|
| 27 |
-
"_load_in_8bit": true,
|
| 28 |
-
"bnb_4bit_compute_dtype": "float32",
|
| 29 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 30 |
-
"bnb_4bit_quant_type": "fp4",
|
| 31 |
-
"bnb_4bit_use_double_quant": false,
|
| 32 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 33 |
-
"llm_int8_has_fp16_weight": false,
|
| 34 |
-
"llm_int8_skip_modules": null,
|
| 35 |
-
"llm_int8_threshold": 6.0,
|
| 36 |
-
"load_in_4bit": false,
|
| 37 |
-
"load_in_8bit": true,
|
| 38 |
-
"quant_method": "bitsandbytes"
|
| 39 |
-
},
|
| 40 |
"query_pre_attn_scalar": 256,
|
| 41 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 42 |
"rope_theta": 10000.0,
|
| 43 |
"sliding_window": 4096,
|
| 44 |
"sliding_window_size": 4096,
|
| 45 |
-
"torch_dtype": "
|
| 46 |
-
"transformers_version": "4.
|
|
|
|
| 47 |
"use_cache": true,
|
| 48 |
-
"vocab_size":
|
| 49 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
|
| 3 |
"architectures": [
|
| 4 |
"Gemma2ForCausalLM"
|
| 5 |
],
|
|
|
|
| 22 |
"num_hidden_layers": 42,
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"query_pre_attn_scalar": 256,
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
"rope_theta": 10000.0,
|
| 29 |
"sliding_window": 4096,
|
| 30 |
"sliding_window_size": 4096,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.46.3",
|
| 33 |
+
"unsloth_version": "2024.12.4",
|
| 34 |
"use_cache": true,
|
| 35 |
+
"vocab_size": 256000
|
| 36 |
}
|
generation_config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"cache_implementation": "hybrid",
|
| 5 |
"eos_token_id": 1,
|
|
|
|
| 6 |
"pad_token_id": 0,
|
| 7 |
-
"transformers_version": "4.
|
| 8 |
}
|
|
|
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"cache_implementation": "hybrid",
|
| 5 |
"eos_token_id": 1,
|
| 6 |
+
"max_length": 8192,
|
| 7 |
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.46.3"
|
| 9 |
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9756e5216fe72e4b485402b96612ff5bf437f8579582b62d4c477c7140a9e247
|
| 3 |
+
size 4903351912
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:600f3a5b94b53bef3e41403c011b69ca0f5d83c34b388c2d8f09ec5e49d4ab3b
|
| 3 |
+
size 4947570872
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e02913fd04d1a130e66135c3ba6fadd4a60bc631c98d745ca97478f9a3cccad
|
| 3 |
+
size 4962221464
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4467950d21fa367584c33554c9d861edb4bce609b552b1bb1b0bd04513c95a83
|
| 3 |
+
size 3670322200
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|