Mustapha
commited on
Commit
·
a9adaf9
1
Parent(s):
4eda650
Upload model
Browse files- README.md +4 -3
- adapter_config.json +8 -8
- adapter_model.safetensors +3 -0
README.md
CHANGED
@@ -18,6 +18,7 @@ base_model: meta-llama/Llama-2-7b-chat-hf
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
|
|
21 |
- **Shared by [optional]:** [More Information Needed]
|
22 |
- **Model type:** [More Information Needed]
|
23 |
- **Language(s) (NLP):** [More Information Needed]
|
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
|
|
76 |
|
77 |
### Training Data
|
78 |
|
79 |
-
<!-- This should link to a
|
80 |
|
81 |
[More Information Needed]
|
82 |
|
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
|
|
107 |
|
108 |
#### Testing Data
|
109 |
|
110 |
-
<!-- This should link to a
|
111 |
|
112 |
[More Information Needed]
|
113 |
|
@@ -216,4 +217,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
219 |
-
- PEFT 0.6.
|
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
- **Shared by [optional]:** [More Information Needed]
|
23 |
- **Model type:** [More Information Needed]
|
24 |
- **Language(s) (NLP):** [More Information Needed]
|
|
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
|
|
108 |
|
109 |
#### Testing Data
|
110 |
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
|
113 |
[More Information Needed]
|
114 |
|
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
220 |
+
- PEFT 0.6.3.dev0
|
adapter_config.json
CHANGED
@@ -16,18 +16,18 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
|
|
|
|
20 |
"self_attn.o_proj",
|
|
|
21 |
"mlp.up_proj",
|
22 |
-
"
|
23 |
-
"self_attn.v_proj",
|
24 |
-
"lm_head.weight",
|
25 |
"self_attn.q_proj",
|
26 |
-
"
|
27 |
-
"model.norm.weight",
|
28 |
-
"self_attn.k_proj",
|
29 |
"self_attn.rotary_emb.inv_freq",
|
30 |
-
"
|
|
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM"
|
33 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"model.norm.weight",
|
20 |
+
"post_attention_layernorm.weight",
|
21 |
+
"self_attn.k_proj",
|
22 |
"self_attn.o_proj",
|
23 |
+
"mlp.gate_proj",
|
24 |
"mlp.up_proj",
|
25 |
+
"input_layernorm.weight",
|
|
|
|
|
26 |
"self_attn.q_proj",
|
27 |
+
"mlp.down_proj",
|
|
|
|
|
28 |
"self_attn.rotary_emb.inv_freq",
|
29 |
+
"self_attn.v_proj",
|
30 |
+
"lm_head.weight"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM"
|
33 |
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c72e9f5a30695b22a9e18ac290542d9fc8dbb2db7a780a3e36ee36ca3efeef3
|
3 |
+
size 159967880
|