Upload 4 files
Browse files- README.md +6 -3
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- config.json +29 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
library_name:
|
3 |
-
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
@@ -15,7 +15,7 @@ tags: []
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
18 |
-
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
@@ -199,3 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
199 |
[More Information Needed]
|
200 |
|
201 |
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: NousResearch/Llama-2-7b-hf
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
18 |
+
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
199 |
[More Information Needed]
|
200 |
|
201 |
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.7.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"gate_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"q_proj",
|
27 |
+
"o_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be6ac93cef06383faa382bf110ae91a57bed53ced0bc75ac998d01228417c329
|
3 |
+
size 159967880
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NousResearch/Llama-2-7b-hf",
|
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": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 32,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.37.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|