Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +2 -0
- config.json +3 -14
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +1 -1
- model.safetensors.index.json +1 -1
README.md
CHANGED
@@ -9,6 +9,8 @@ tags:
|
|
9 |
- llama
|
10 |
- trl
|
11 |
- sft
|
|
|
|
|
12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
13 |
---
|
14 |
|
|
|
9 |
- llama
|
10 |
- trl
|
11 |
- sft
|
12 |
+
- 4bit
|
13 |
+
- LoRA
|
14 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
15 |
---
|
16 |
|
config.json
CHANGED
@@ -12,30 +12,19 @@
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
"max_position_embeddings": 8192,
|
|
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
"pretraining_tp": 1,
|
20 |
-
"quantization_config": {
|
21 |
-
"bnb_4bit_compute_dtype": "float16",
|
22 |
-
"bnb_4bit_quant_type": "nf4",
|
23 |
-
"bnb_4bit_use_double_quant": true,
|
24 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
-
"llm_int8_has_fp16_weight": false,
|
26 |
-
"llm_int8_skip_modules": null,
|
27 |
-
"llm_int8_threshold": 6.0,
|
28 |
-
"load_in_4bit": true,
|
29 |
-
"load_in_8bit": false,
|
30 |
-
"quant_method": "bitsandbytes"
|
31 |
-
},
|
32 |
"rms_norm_eps": 1e-05,
|
33 |
"rope_scaling": null,
|
34 |
"rope_theta": 500000.0,
|
35 |
"tie_word_embeddings": false,
|
36 |
"torch_dtype": "float16",
|
37 |
-
"transformers_version": "4.
|
38 |
-
"unsloth_version": "2024.
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 128256
|
41 |
}
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.41.2",
|
27 |
+
"unsloth_version": "2024.6",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 128256
|
30 |
}
|
generation_config.json
CHANGED
@@ -5,5 +5,5 @@
|
|
5 |
"max_length": 4096,
|
6 |
"temperature": 0.6,
|
7 |
"top_p": 0.9,
|
8 |
-
"transformers_version": "4.
|
9 |
}
|
|
|
5 |
"max_length": 4096,
|
6 |
"temperature": 0.6,
|
7 |
"top_p": 0.9,
|
8 |
+
"transformers_version": "4.41.2"
|
9 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bae7df22d0b80b4bd43df58f7a6a4a5f7cf394aea2ba0fafe0662d01c639530d
|
3 |
+
size 4652072866
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1050673280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
|
3 |
size 1050673280
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 5702577746
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|