Hugging Face's logo

922-CA
/
monika-lm-lora-tests

Safetensors
GGUF
Model card Files Community
922CA commited on
Commit
4236c27
·
1 Parent(s): 3b4d8e6

Upload 12 files

Browse files
Files changed (12) hide show
  1. l2-7b-monika-v0.3i-Kv2-b/README.md +20 -0
  2. l2-7b-monika-v0.3i-Kv2-b/adapter_config.json +21 -0
  3. l2-7b-monika-v0.3i-Kv2-b/adapter_model.bin +3 -0
  4. l2-7b-monika-v0.3i-Kv2-b/ggml-adapter-model.bin +3 -0
  5. l2-7b-monika-v0.3i-Kv2-c/README.md +20 -0
  6. l2-7b-monika-v0.3i-Kv2-c/adapter_config.json +21 -0
  7. l2-7b-monika-v0.3i-Kv2-c/adapter_model.bin +3 -0
  8. l2-7b-monika-v0.3i-Kv2-c/ggml-adapter-model.bin +3 -0
  9. l2-7b-monika-v0.3m/README.md +20 -0
  10. l2-7b-monika-v0.3m/adapter_config.json +21 -0
  11. l2-7b-monika-v0.3m/adapter_model.bin +3 -0
  12. l2-7b-monika-v0.3m/ggml-adapter-model.bin +3 -0
l2-7b-monika-v0.3i-Kv2-b/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
l2-7b-monika-v0.3i-Kv2-b/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "johnwick123forevr/Llama2-chat-kimiko-Sharded-2gb",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 64,
11
+ "lora_dropout": 0.5,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
l2-7b-monika-v0.3i-Kv2-b/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0480a21ecdc29ca6afd4a76523db98094f6a42d813c0ee78d7800a8108a17b7f
3
+ size 67154893
l2-7b-monika-v0.3i-Kv2-b/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152639e1e0d78429218eabd865dc79cbcbe225f77322ac7baab5239516eaca47
3
+ size 67117088
l2-7b-monika-v0.3i-Kv2-c/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
l2-7b-monika-v0.3i-Kv2-c/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "johnwick123forevr/Llama2-chat-kimiko-Sharded-2gb",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 64,
11
+ "lora_dropout": 0.5,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
l2-7b-monika-v0.3i-Kv2-c/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35aadd3314bb5ef63f53f43f42fb520d58c0c385b58fa9098a77b01512c121d3
3
+ size 67154893
l2-7b-monika-v0.3i-Kv2-c/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b4faed31e326ae6cb886ef03d84ae1f66eec54184be1b06d8990a83076f582
3
+ size 67117088
l2-7b-monika-v0.3m/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
l2-7b-monika-v0.3m/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "fengtc/Llama-2-7b-chat-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 64,
11
+ "lora_dropout": 0.5,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
l2-7b-monika-v0.3m/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b43953e3926536010c1f9b2e3f3b62e919ff4953524f205457cb20406a208b
3
+ size 67154893
l2-7b-monika-v0.3m/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7196d525e57194f612aaabe17f92403afd5a87530e81cc23c39aa56106346f32
3
+ size 67117088