Commit
•
224363a
1
Parent(s):
3cd2437
End of training
Browse files
README.md
CHANGED
|
@@ -11,6 +11,7 @@ tags:
|
|
| 11 |
- unsloth
|
| 12 |
- unsloth
|
| 13 |
- unsloth
|
|
|
|
| 14 |
base_model: unsloth/gemma-7b-bnb-4bit
|
| 15 |
model-index:
|
| 16 |
- name: outputs
|
|
|
|
| 11 |
- unsloth
|
| 12 |
- unsloth
|
| 13 |
- unsloth
|
| 14 |
+
- unsloth
|
| 15 |
base_model: unsloth/gemma-7b-bnb-4bit
|
| 16 |
model-index:
|
| 17 |
- name: outputs
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 200068512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a41300eb7038ddbb5f1de6316ec985f110f9a32e17fa6d650d74814a96a70d5
|
| 3 |
size 200068512
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "unsloth/gemma-7b-bnb-4bit",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GemmaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"eos_token_id": 1,
|
| 10 |
+
"head_dim": 256,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_size": 3072,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 24576,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"model_type": "gemma",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 16,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 23 |
+
"bnb_4bit_quant_type": "nf4",
|
| 24 |
+
"bnb_4bit_use_double_quant": true,
|
| 25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 26 |
+
"llm_int8_has_fp16_weight": false,
|
| 27 |
+
"llm_int8_skip_modules": null,
|
| 28 |
+
"llm_int8_threshold": 6.0,
|
| 29 |
+
"load_in_4bit": true,
|
| 30 |
+
"load_in_8bit": false,
|
| 31 |
+
"quant_method": "bitsandbytes"
|
| 32 |
+
},
|
| 33 |
+
"rms_norm_eps": 1e-06,
|
| 34 |
+
"rope_scaling": null,
|
| 35 |
+
"rope_theta": 10000.0,
|
| 36 |
+
"torch_dtype": "float16",
|
| 37 |
+
"transformers_version": "4.38.2",
|
| 38 |
+
"unsloth_version": "2024.4",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 256000
|
| 41 |
+
}
|
runs/Apr16_12-34-50_e99f7f5e82fa/events.out.tfevents.1713272609.e99f7f5e82fa.251.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5631d14bf6413dc54dde331a7886bfa7bec35a79f81acc70d769a78b449d43e8
|
| 3 |
+
size 26027
|