HF中国镜像站's logo

922-CA
/
monika-lm-lora-tests

Model card Files Community
922CA commited on
Commit
40d545b
·
1 Parent(s): bccea64

Upload 12 files

Browse files
Files changed (12) hide show
  1. llama-2-7b-chat-monika-v0.3/README.md +20 -0
  2. llama-2-7b-chat-monika-v0.3/adapter_config.json +21 -0
  3. llama-2-7b-chat-monika-v0.3/adapter_model.bin +3 -0
  4. llama-2-7b-chat-monika-v0.3/ggml-adapter-model.bin +3 -0
  5. llama-2-7b-chat-monika-v0.3a/README.md +20 -0
  6. llama-2-7b-chat-monika-v0.3a/adapter_config.json +21 -0
  7. llama-2-7b-chat-monika-v0.3a/adapter_model.bin +3 -0
  8. llama-2-7b-chat-monika-v0.3a/ggml-adapter-model.bin +3 -0
  9. llama-2-7b-chat-monika-v0.3b/README.md +20 -0
  10. llama-2-7b-chat-monika-v0.3b/adapter_config.json +21 -0
  11. llama-2-7b-chat-monika-v0.3b/adapter_model.bin +3 -0
  12. llama-2-7b-chat-monika-v0.3b/ggml-adapter-model.bin +3 -0
llama-2-7b-chat-monika-v0.3/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
llama-2-7b-chat-monika-v0.3/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-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": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
llama-2-7b-chat-monika-v0.3/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27216d77db527e045bd51ec7aad595a305841f2da53045266813b312b4b03ba
3
+ size 134263757
llama-2-7b-chat-monika-v0.3/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e67fe4f7dcd61ec974da2d5968fcddfffc9a638b855774e0a76edbf01539ef2
3
+ size 134225952
llama-2-7b-chat-monika-v0.3a/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
llama-2-7b-chat-monika-v0.3a/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": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
llama-2-7b-chat-monika-v0.3a/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffeff7d68694322d32e727b7790413ed2619fd43e2de52c04d092138d0bf793
3
+ size 134263757
llama-2-7b-chat-monika-v0.3a/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0785afae78811a6c1afe1cf331c7bac191bedc2b7f70f63e4ed06dce51dbbd8c
3
+ size 134225952
llama-2-7b-chat-monika-v0.3b/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
llama-2-7b-chat-monika-v0.3b/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": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
llama-2-7b-chat-monika-v0.3b/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2ce5f2e69910e6c489a667491c517694b68bf5fbbe842d0f8b149e1d1977b4
3
+ size 134263757
llama-2-7b-chat-monika-v0.3b/ggml-adapter-model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0433e92cafb721f054621a153cd597fef87f83abba242fffa59c9a34f7e4a512
3
+ size 134225952