Update README.md
Browse files
README.md
CHANGED
@@ -55,7 +55,7 @@ base_model: /workspace/models/Mistral-Small-Instruct-2409
|
|
55 |
model_type: AutoModelForCausalLM
|
56 |
tokenizer_type: AutoTokenizer
|
57 |
|
58 |
-
hub_model_id: anthracite-
|
59 |
hub_strategy: "all_checkpoints"
|
60 |
push_dataset_to_hub:
|
61 |
hf_use_auth_token: true
|
@@ -73,17 +73,17 @@ load_in_4bit: false
|
|
73 |
strict: false
|
74 |
|
75 |
datasets:
|
76 |
-
- path: anthracite-
|
77 |
type: custommistralv2v3
|
78 |
-
- path: anthracite-
|
79 |
type: custommistralv2v3
|
80 |
-
- path: anthracite-
|
81 |
type: custommistralv2v3
|
82 |
- path: anthracite-org/nopm_claude_writing_fixed
|
83 |
type: custommistralv2v3
|
84 |
-
- path: anthracite-
|
85 |
type: custommistralv2v3
|
86 |
-
- path: anthracite-
|
87 |
type: custommistralv2v3
|
88 |
#chat_template: mistral_v2v3
|
89 |
shuffle_merged_datasets: true
|
@@ -151,12 +151,12 @@ We'd like to thank Recursal / Featherless for sponsoring the compute for this tr
|
|
151 |
We would also like to thank all members of Anthracite who made this finetune possible.
|
152 |
|
153 |
## Datasets
|
154 |
-
- [anthracite-
|
155 |
-
- [anthracite-
|
156 |
-
- [anthracite-
|
157 |
- [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
|
158 |
-
- [anthracite-
|
159 |
-
- [anthracite-
|
160 |
|
161 |
## Training
|
162 |
The training was done for 2 epochs. We used 8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) for the full-parameter fine-tuning of the model.
|
|
|
55 |
model_type: AutoModelForCausalLM
|
56 |
tokenizer_type: AutoTokenizer
|
57 |
|
58 |
+
hub_model_id: anthracite-org/magnum-v4-22b-r4
|
59 |
hub_strategy: "all_checkpoints"
|
60 |
push_dataset_to_hub:
|
61 |
hf_use_auth_token: true
|
|
|
73 |
strict: false
|
74 |
|
75 |
datasets:
|
76 |
+
- path: anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
|
77 |
type: custommistralv2v3
|
78 |
+
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
|
79 |
type: custommistralv2v3
|
80 |
+
- path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
|
81 |
type: custommistralv2v3
|
82 |
- path: anthracite-org/nopm_claude_writing_fixed
|
83 |
type: custommistralv2v3
|
84 |
+
- path: anthracite-org/kalo_opus_misc_240827_no_system
|
85 |
type: custommistralv2v3
|
86 |
+
- path: anthracite-org/kalo_misc_part2_no_system
|
87 |
type: custommistralv2v3
|
88 |
#chat_template: mistral_v2v3
|
89 |
shuffle_merged_datasets: true
|
|
|
151 |
We would also like to thank all members of Anthracite who made this finetune possible.
|
152 |
|
153 |
## Datasets
|
154 |
+
- [anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system](https://huggingface.co/datasets/anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system)
|
155 |
+
- [anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system)
|
156 |
+
- [anthracite-org/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-3k-filtered-no-system)
|
157 |
- [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
|
158 |
+
- [anthracite-org/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827_no_system)
|
159 |
+
- [anthracite-org/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2_no_system)
|
160 |
|
161 |
## Training
|
162 |
The training was done for 2 epochs. We used 8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) for the full-parameter fine-tuning of the model.
|