|
--- |
|
base_model: mistralai/Mistral-Nemo-Base-2407 |
|
language: |
|
- en |
|
- fr |
|
- de |
|
- es |
|
- it |
|
- pt |
|
- ru |
|
- zh |
|
- ja |
|
license: apache-2.0 |
|
extra_gated_description: If you want to learn more about how we process your personal |
|
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>. |
|
model-index: |
|
- name: Mistral-Nemo-Instruct-2407 |
|
results: |
|
- task: |
|
type: squad_answerable-judge |
|
dataset: |
|
name: squad_answerable |
|
type: multi-choices |
|
metrics: |
|
- type: judge_match |
|
value: '0.685' |
|
args: |
|
results: |
|
squad_answerable-judge: |
|
exact_match,strict_match: 0.6852522530110334 |
|
exact_match_stderr,strict_match: 0.004262305820311226 |
|
alias: squad_answerable-judge |
|
context_has_answer-judge: |
|
exact_match,strict_match: 0.7906976744186046 |
|
exact_match_stderr,strict_match: 0.04412480456048906 |
|
alias: context_has_answer-judge |
|
group_subtasks: |
|
context_has_answer-judge: [] |
|
squad_answerable-judge: [] |
|
configs: |
|
context_has_answer-judge: |
|
task: context_has_answer-judge |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: context_has_answer_judge |
|
test_split: test |
|
doc_to_text: '<s>[INST]You are asked to determine if a question has the |
|
answer in the context, and answer with a simple Yes or No. |
|
|
|
|
|
Example: |
|
|
|
Question: How is the weather today? Context: How is the traffic today? |
|
It is horrible. Does the question have the answer in the Context? |
|
|
|
Answer: No |
|
|
|
Question: How is the weather today? Context: Is the weather good today? |
|
Yes, it is sunny. Does the question have the answer in the Context? |
|
|
|
Answer: Yes |
|
|
|
|
|
Question: {{question}} |
|
|
|
Context: {{similar_question}} {{similar_answer}} |
|
|
|
Does the question have the answer in the Context? |
|
|
|
[/INST]' |
|
doc_to_target: '{{''Yes'' if is_relevant in [''Yes'', 1] else ''No''}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: exact_match |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- <|im_end|> |
|
do_sample: false |
|
temperature: 0.3 |
|
repeats: 1 |
|
filter_list: |
|
- name: strict_match |
|
filter: |
|
- function: regex |
|
regex_pattern: Yes|No |
|
group_select: -1 |
|
- function: take_first |
|
should_decontaminate: false |
|
squad_answerable-judge: |
|
task: squad_answerable-judge |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: squad_answerable_judge |
|
test_split: test |
|
doc_to_text: '<s>[INST]You are asked to determine if a question has the |
|
answer in the context, and answer with a simple Yes or No. |
|
|
|
|
|
Example: |
|
|
|
Question: How is the weather today? Context: The traffic is horrible. |
|
Does the question have the answer in the Context? |
|
|
|
Answer: No |
|
|
|
Question: How is the weather today? Context: The weather is good. Does |
|
the question have the answer in the Context? |
|
|
|
Answer: Yes |
|
|
|
|
|
Question: {{question}} |
|
|
|
Context: {{context}} |
|
|
|
Does the question have the answer in the Context? |
|
|
|
[/INST]' |
|
doc_to_target: '{{''Yes'' if is_relevant in [''Yes'', 1] else ''No''}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: exact_match |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- <|im_end|> |
|
do_sample: false |
|
temperature: 0.3 |
|
repeats: 1 |
|
filter_list: |
|
- name: strict_match |
|
filter: |
|
- function: regex |
|
regex_pattern: Yes|No |
|
group_select: -1 |
|
- function: take_first |
|
should_decontaminate: false |
|
versions: |
|
context_has_answer-judge: Yaml |
|
squad_answerable-judge: Yaml |
|
n-shot: {} |
|
config: |
|
model: vllm |
|
model_args: pretrained=mistralai/Mistral-Nemo-Instruct-2407,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8,max_model_len=2048,trust_remote_code=True |
|
batch_size: auto |
|
batch_sizes: [] |
|
bootstrap_iters: 100000 |
|
git_hash: cddf85d |
|
pretty_env_info: 'PyTorch version: 2.4.0+cu121 |
|
|
|
Is debug build: False |
|
|
|
CUDA used to build PyTorch: 12.1 |
|
|
|
ROCM used to build PyTorch: N/A |
|
|
|
|
|
OS: Ubuntu 22.04.3 LTS (x86_64) |
|
|
|
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 |
|
|
|
Clang version: Could not collect |
|
|
|
CMake version: version 3.25.0 |
|
|
|
Libc version: glibc-2.35 |
|
|
|
|
|
Python version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit |
|
runtime) |
|
|
|
Python platform: Linux-5.4.0-149-generic-x86_64-with-glibc2.35 |
|
|
|
Is CUDA available: True |
|
|
|
CUDA runtime version: 11.8.89 |
|
|
|
CUDA_MODULE_LOADING set to: LAZY |
|
|
|
GPU models and configuration: GPU 0: NVIDIA L40 |
|
|
|
Nvidia driver version: 535.54.03 |
|
|
|
cuDNN version: Could not collect |
|
|
|
HIP runtime version: N/A |
|
|
|
MIOpen runtime version: N/A |
|
|
|
Is XNNPACK available: True |
|
|
|
|
|
CPU: |
|
|
|
Architecture: x86_64 |
|
|
|
CPU op-mode(s): 32-bit, 64-bit |
|
|
|
Address sizes: 48 bits physical, 48 bits virtual |
|
|
|
Byte Order: Little Endian |
|
|
|
CPU(s): 256 |
|
|
|
On-line CPU(s) list: 0-254 |
|
|
|
Off-line CPU(s) list: 255 |
|
|
|
Vendor ID: AuthenticAMD |
|
|
|
Model name: AMD EPYC 7773X 64-Core Processor |
|
|
|
CPU family: 25 |
|
|
|
Model: 1 |
|
|
|
Thread(s) per core: 2 |
|
|
|
Core(s) per socket: 64 |
|
|
|
Socket(s): 2 |
|
|
|
Stepping: 2 |
|
|
|
Frequency boost: enabled |
|
|
|
CPU max MHz: 2200.0000 |
|
|
|
CPU min MHz: 0.0000 |
|
|
|
BogoMIPS: 4400.14 |
|
|
|
Flags: fpu vme de pse tsc msr pae mce cx8 apic |
|
sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx |
|
mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc |
|
cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 |
|
sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy |
|
svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit |
|
wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 |
|
cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase |
|
bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni |
|
xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local |
|
clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale |
|
vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload |
|
vgif umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca |
|
|
|
Virtualization: AMD-V |
|
|
|
L1d cache: 4 MiB (128 instances) |
|
|
|
L1i cache: 4 MiB (128 instances) |
|
|
|
L2 cache: 64 MiB (128 instances) |
|
|
|
L3 cache: 1.5 GiB (16 instances) |
|
|
|
NUMA node(s): 16 |
|
|
|
NUMA node0 CPU(s): 0-7,128-135 |
|
|
|
NUMA node1 CPU(s): 8-15,136-143 |
|
|
|
NUMA node2 CPU(s): 16-23,144-151 |
|
|
|
NUMA node3 CPU(s): 24-31,152-159 |
|
|
|
NUMA node4 CPU(s): 32-39,160-167 |
|
|
|
NUMA node5 CPU(s): 40-47,168-175 |
|
|
|
NUMA node6 CPU(s): 48-55,176-183 |
|
|
|
NUMA node7 CPU(s): 56-63,184-191 |
|
|
|
NUMA node8 CPU(s): 64-71,192-199 |
|
|
|
NUMA node9 CPU(s): 72-79,200-207 |
|
|
|
NUMA node10 CPU(s): 80-87,208-215 |
|
|
|
NUMA node11 CPU(s): 88-95,216-223 |
|
|
|
NUMA node12 CPU(s): 96-103,224-231 |
|
|
|
NUMA node13 CPU(s): 104-111,232-239 |
|
|
|
NUMA node14 CPU(s): 112-119,240-247 |
|
|
|
NUMA node15 CPU(s): 120-127,248-254 |
|
|
|
Vulnerability Itlb multihit: Not affected |
|
|
|
Vulnerability L1tf: Not affected |
|
|
|
Vulnerability Mds: Not affected |
|
|
|
Vulnerability Meltdown: Not affected |
|
|
|
Vulnerability Mmio stale data: Not affected |
|
|
|
Vulnerability Retbleed: Not affected |
|
|
|
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled |
|
via prctl and seccomp |
|
|
|
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and |
|
__user pointer sanitization |
|
|
|
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, |
|
IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected |
|
|
|
Vulnerability Srbds: Not affected |
|
|
|
Vulnerability Tsx async abort: Not affected |
|
|
|
|
|
Versions of relevant libraries: |
|
|
|
[pip3] numpy==1.24.1 |
|
|
|
[pip3] torch==2.4.0 |
|
|
|
[pip3] torchaudio==2.0.2+cu118 |
|
|
|
[pip3] torchvision==0.19.0 |
|
|
|
[pip3] triton==3.0.0 |
|
|
|
[conda] Could not collect' |
|
transformers_version: 4.44.1 |
|
- task: |
|
type: context_has_answer-judge |
|
dataset: |
|
name: context_has_answer |
|
type: multi-choices |
|
metrics: |
|
- type: judge_match |
|
value: '0.791' |
|
args: |
|
results: |
|
squad_answerable-judge: |
|
exact_match,strict_match: 0.6852522530110334 |
|
exact_match_stderr,strict_match: 0.004262305820311226 |
|
alias: squad_answerable-judge |
|
context_has_answer-judge: |
|
exact_match,strict_match: 0.7906976744186046 |
|
exact_match_stderr,strict_match: 0.04412480456048906 |
|
alias: context_has_answer-judge |
|
group_subtasks: |
|
context_has_answer-judge: [] |
|
squad_answerable-judge: [] |
|
configs: |
|
context_has_answer-judge: |
|
task: context_has_answer-judge |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: context_has_answer_judge |
|
test_split: test |
|
doc_to_text: '<s>[INST]You are asked to determine if a question has the |
|
answer in the context, and answer with a simple Yes or No. |
|
|
|
|
|
Example: |
|
|
|
Question: How is the weather today? Context: How is the traffic today? |
|
It is horrible. Does the question have the answer in the Context? |
|
|
|
Answer: No |
|
|
|
Question: How is the weather today? Context: Is the weather good today? |
|
Yes, it is sunny. Does the question have the answer in the Context? |
|
|
|
Answer: Yes |
|
|
|
|
|
Question: {{question}} |
|
|
|
Context: {{similar_question}} {{similar_answer}} |
|
|
|
Does the question have the answer in the Context? |
|
|
|
[/INST]' |
|
doc_to_target: '{{''Yes'' if is_relevant in [''Yes'', 1] else ''No''}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: exact_match |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- <|im_end|> |
|
do_sample: false |
|
temperature: 0.3 |
|
repeats: 1 |
|
filter_list: |
|
- name: strict_match |
|
filter: |
|
- function: regex |
|
regex_pattern: Yes|No |
|
group_select: -1 |
|
- function: take_first |
|
should_decontaminate: false |
|
squad_answerable-judge: |
|
task: squad_answerable-judge |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: squad_answerable_judge |
|
test_split: test |
|
doc_to_text: '<s>[INST]You are asked to determine if a question has the |
|
answer in the context, and answer with a simple Yes or No. |
|
|
|
|
|
Example: |
|
|
|
Question: How is the weather today? Context: The traffic is horrible. |
|
Does the question have the answer in the Context? |
|
|
|
Answer: No |
|
|
|
Question: How is the weather today? Context: The weather is good. Does |
|
the question have the answer in the Context? |
|
|
|
Answer: Yes |
|
|
|
|
|
Question: {{question}} |
|
|
|
Context: {{context}} |
|
|
|
Does the question have the answer in the Context? |
|
|
|
[/INST]' |
|
doc_to_target: '{{''Yes'' if is_relevant in [''Yes'', 1] else ''No''}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: exact_match |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- <|im_end|> |
|
do_sample: false |
|
temperature: 0.3 |
|
repeats: 1 |
|
filter_list: |
|
- name: strict_match |
|
filter: |
|
- function: regex |
|
regex_pattern: Yes|No |
|
group_select: -1 |
|
- function: take_first |
|
should_decontaminate: false |
|
versions: |
|
context_has_answer-judge: Yaml |
|
squad_answerable-judge: Yaml |
|
n-shot: {} |
|
config: |
|
model: vllm |
|
model_args: pretrained=mistralai/Mistral-Nemo-Instruct-2407,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8,max_model_len=2048,trust_remote_code=True |
|
batch_size: auto |
|
batch_sizes: [] |
|
bootstrap_iters: 100000 |
|
git_hash: cddf85d |
|
pretty_env_info: 'PyTorch version: 2.4.0+cu121 |
|
|
|
Is debug build: False |
|
|
|
CUDA used to build PyTorch: 12.1 |
|
|
|
ROCM used to build PyTorch: N/A |
|
|
|
|
|
OS: Ubuntu 22.04.3 LTS (x86_64) |
|
|
|
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 |
|
|
|
Clang version: Could not collect |
|
|
|
CMake version: version 3.25.0 |
|
|
|
Libc version: glibc-2.35 |
|
|
|
|
|
Python version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit |
|
runtime) |
|
|
|
Python platform: Linux-5.4.0-149-generic-x86_64-with-glibc2.35 |
|
|
|
Is CUDA available: True |
|
|
|
CUDA runtime version: 11.8.89 |
|
|
|
CUDA_MODULE_LOADING set to: LAZY |
|
|
|
GPU models and configuration: GPU 0: NVIDIA L40 |
|
|
|
Nvidia driver version: 535.54.03 |
|
|
|
cuDNN version: Could not collect |
|
|
|
HIP runtime version: N/A |
|
|
|
MIOpen runtime version: N/A |
|
|
|
Is XNNPACK available: True |
|
|
|
|
|
CPU: |
|
|
|
Architecture: x86_64 |
|
|
|
CPU op-mode(s): 32-bit, 64-bit |
|
|
|
Address sizes: 48 bits physical, 48 bits virtual |
|
|
|
Byte Order: Little Endian |
|
|
|
CPU(s): 256 |
|
|
|
On-line CPU(s) list: 0-254 |
|
|
|
Off-line CPU(s) list: 255 |
|
|
|
Vendor ID: AuthenticAMD |
|
|
|
Model name: AMD EPYC 7773X 64-Core Processor |
|
|
|
CPU family: 25 |
|
|
|
Model: 1 |
|
|
|
Thread(s) per core: 2 |
|
|
|
Core(s) per socket: 64 |
|
|
|
Socket(s): 2 |
|
|
|
Stepping: 2 |
|
|
|
Frequency boost: enabled |
|
|
|
CPU max MHz: 2200.0000 |
|
|
|
CPU min MHz: 0.0000 |
|
|
|
BogoMIPS: 4400.14 |
|
|
|
Flags: fpu vme de pse tsc msr pae mce cx8 apic |
|
sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx |
|
mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc |
|
cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 |
|
sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy |
|
svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit |
|
wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 |
|
cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase |
|
bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni |
|
xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local |
|
clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale |
|
vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload |
|
vgif umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca |
|
|
|
Virtualization: AMD-V |
|
|
|
L1d cache: 4 MiB (128 instances) |
|
|
|
L1i cache: 4 MiB (128 instances) |
|
|
|
L2 cache: 64 MiB (128 instances) |
|
|
|
L3 cache: 1.5 GiB (16 instances) |
|
|
|
NUMA node(s): 16 |
|
|
|
NUMA node0 CPU(s): 0-7,128-135 |
|
|
|
NUMA node1 CPU(s): 8-15,136-143 |
|
|
|
NUMA node2 CPU(s): 16-23,144-151 |
|
|
|
NUMA node3 CPU(s): 24-31,152-159 |
|
|
|
NUMA node4 CPU(s): 32-39,160-167 |
|
|
|
NUMA node5 CPU(s): 40-47,168-175 |
|
|
|
NUMA node6 CPU(s): 48-55,176-183 |
|
|
|
NUMA node7 CPU(s): 56-63,184-191 |
|
|
|
NUMA node8 CPU(s): 64-71,192-199 |
|
|
|
NUMA node9 CPU(s): 72-79,200-207 |
|
|
|
NUMA node10 CPU(s): 80-87,208-215 |
|
|
|
NUMA node11 CPU(s): 88-95,216-223 |
|
|
|
NUMA node12 CPU(s): 96-103,224-231 |
|
|
|
NUMA node13 CPU(s): 104-111,232-239 |
|
|
|
NUMA node14 CPU(s): 112-119,240-247 |
|
|
|
NUMA node15 CPU(s): 120-127,248-254 |
|
|
|
Vulnerability Itlb multihit: Not affected |
|
|
|
Vulnerability L1tf: Not affected |
|
|
|
Vulnerability Mds: Not affected |
|
|
|
Vulnerability Meltdown: Not affected |
|
|
|
Vulnerability Mmio stale data: Not affected |
|
|
|
Vulnerability Retbleed: Not affected |
|
|
|
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled |
|
via prctl and seccomp |
|
|
|
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and |
|
__user pointer sanitization |
|
|
|
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, |
|
IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected |
|
|
|
Vulnerability Srbds: Not affected |
|
|
|
Vulnerability Tsx async abort: Not affected |
|
|
|
|
|
Versions of relevant libraries: |
|
|
|
[pip3] numpy==1.24.1 |
|
|
|
[pip3] torch==2.4.0 |
|
|
|
[pip3] torchaudio==2.0.2+cu118 |
|
|
|
[pip3] torchvision==0.19.0 |
|
|
|
[pip3] triton==3.0.0 |
|
|
|
[conda] Could not collect' |
|
transformers_version: 4.44.1 |
|
--- |
|
### Needle in a Haystack Evaluation Heatmap |
|
|
|
 |
|
|
|
 |
|
|
|
|
|
# Model Card for Mistral-Nemo-Instruct-2407 |
|
|
|
The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407). Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size. |
|
|
|
For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-nemo/). |
|
|
|
## Key features |
|
- Released under the **Apache 2 License** |
|
- Pre-trained and instructed versions |
|
- Trained with a **128k context window** |
|
- Trained on a large proportion of **multilingual and code data** |
|
- Drop-in replacement of Mistral 7B |
|
|
|
## Model Architecture |
|
Mistral Nemo is a transformer model, with the following architecture choices: |
|
- **Layers:** 40 |
|
- **Dim:** 5,120 |
|
- **Head dim:** 128 |
|
- **Hidden dim:** 14,336 |
|
- **Activation Function:** SwiGLU |
|
- **Number of heads:** 32 |
|
- **Number of kv-heads:** 8 (GQA) |
|
- **Vocabulary size:** 2**17 ~= 128k |
|
- **Rotary embeddings (theta = 1M)** |
|
|
|
## Metrics |
|
|
|
### Main Benchmarks |
|
|
|
| Benchmark | Score | |
|
| --- | --- | |
|
| HellaSwag (0-shot) | 83.5% | |
|
| Winogrande (0-shot) | 76.8% | |
|
| OpenBookQA (0-shot) | 60.6% | |
|
| CommonSenseQA (0-shot) | 70.4% | |
|
| TruthfulQA (0-shot) | 50.3% | |
|
| MMLU (5-shot) | 68.0% | |
|
| TriviaQA (5-shot) | 73.8% | |
|
| NaturalQuestions (5-shot) | 31.2% | |
|
|
|
### Multilingual Benchmarks (MMLU) |
|
|
|
| Language | Score | |
|
| --- | --- | |
|
| French | 62.3% | |
|
| German | 62.7% | |
|
| Spanish | 64.6% | |
|
| Italian | 61.3% | |
|
| Portuguese | 63.3% | |
|
| Russian | 59.2% | |
|
| Chinese | 59.0% | |
|
| Japanese | 59.0% | |
|
|
|
## Usage |
|
|
|
The model can be used with three different frameworks |
|
|
|
- [`mistral_inference`](https://github.com/mistralai/mistral-inference): See [here](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407#mistral-inference) |
|
- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers) |
|
- [`NeMo`](https://github.com/NVIDIA/NeMo): See [nvidia/Mistral-NeMo-12B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-12B-Instruct) |
|
|
|
### Mistral Inference |
|
|
|
#### Install |
|
|
|
It is recommended to use `mistralai/Mistral-Nemo-Instruct-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling. |
|
|
|
``` |
|
pip install mistral_inference |
|
``` |
|
|
|
#### Download |
|
|
|
```py |
|
from huggingface_hub import snapshot_download |
|
from pathlib import Path |
|
|
|
mistral_models_path = Path.home().joinpath('mistral_models', 'Nemo-Instruct') |
|
mistral_models_path.mkdir(parents=True, exist_ok=True) |
|
|
|
snapshot_download(repo_id="mistralai/Mistral-Nemo-Instruct-2407", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path) |
|
``` |
|
|
|
#### Chat |
|
|
|
After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using |
|
|
|
``` |
|
mistral-chat $HOME/mistral_models/Nemo-Instruct --instruct --max_tokens 256 --temperature 0.35 |
|
``` |
|
|
|
*E.g.* Try out something like: |
|
``` |
|
How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar. |
|
``` |
|
|
|
#### Instruct following |
|
|
|
```py |
|
from mistral_inference.transformer import Transformer |
|
from mistral_inference.generate import generate |
|
|
|
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer |
|
from mistral_common.protocol.instruct.messages import UserMessage |
|
from mistral_common.protocol.instruct.request import ChatCompletionRequest |
|
|
|
tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json") |
|
model = Transformer.from_folder(mistral_models_path) |
|
|
|
prompt = "How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar." |
|
|
|
completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)]) |
|
|
|
tokens = tokenizer.encode_chat_completion(completion_request).tokens |
|
|
|
out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) |
|
result = tokenizer.decode(out_tokens[0]) |
|
|
|
print(result) |
|
``` |
|
|
|
#### Function calling |
|
|
|
```py |
|
from mistral_common.protocol.instruct.tool_calls import Function, Tool |
|
from mistral_inference.transformer import Transformer |
|
from mistral_inference.generate import generate |
|
|
|
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer |
|
from mistral_common.protocol.instruct.messages import UserMessage |
|
from mistral_common.protocol.instruct.request import ChatCompletionRequest |
|
|
|
|
|
tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tekken.json") |
|
model = Transformer.from_folder(mistral_models_path) |
|
|
|
completion_request = ChatCompletionRequest( |
|
tools=[ |
|
Tool( |
|
function=Function( |
|
name="get_current_weather", |
|
description="Get the current weather", |
|
parameters={ |
|
"type": "object", |
|
"properties": { |
|
"location": { |
|
"type": "string", |
|
"description": "The city and state, e.g. San Francisco, CA", |
|
}, |
|
"format": { |
|
"type": "string", |
|
"enum": ["celsius", "fahrenheit"], |
|
"description": "The temperature unit to use. Infer this from the users location.", |
|
}, |
|
}, |
|
"required": ["location", "format"], |
|
}, |
|
) |
|
) |
|
], |
|
messages=[ |
|
UserMessage(content="What's the weather like today in Paris?"), |
|
], |
|
) |
|
|
|
tokens = tokenizer.encode_chat_completion(completion_request).tokens |
|
|
|
out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.35, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) |
|
result = tokenizer.decode(out_tokens[0]) |
|
|
|
print(result) |
|
``` |
|
|
|
### Transformers |
|
|
|
> [!IMPORTANT] |
|
> NOTE: Until a new release has been made, you need to install transformers from source: |
|
> ```sh |
|
> pip install git+https://github.com/huggingface/transformers.git |
|
> ``` |
|
|
|
If you want to use Hugging Face `transformers` to generate text, you can do something like this. |
|
|
|
```py |
|
from transformers import pipeline |
|
|
|
messages = [ |
|
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, |
|
{"role": "user", "content": "Who are you?"}, |
|
] |
|
chatbot = pipeline("text-generation", model="mistralai/Mistral-Nemo-Instruct-2407",max_new_tokens=128) |
|
chatbot(messages) |
|
``` |
|
|
|
## Function calling with `transformers` |
|
|
|
To use this example, you'll need `transformers` version 4.42.0 or higher. Please see the |
|
[function calling guide](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling) |
|
in the `transformers` docs for more information. |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
import torch |
|
|
|
model_id = "mistralai/Mistral-Nemo-Instruct-2407" |
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
def get_current_weather(location: str, format: str): |
|
""" |
|
Get the current weather |
|
|
|
Args: |
|
location: The city and state, e.g. San Francisco, CA |
|
format: The temperature unit to use. Infer this from the users location. (choices: ["celsius", "fahrenheit"]) |
|
""" |
|
pass |
|
|
|
conversation = [{"role": "user", "content": "What's the weather like in Paris?"}] |
|
tools = [get_current_weather] |
|
|
|
# format and tokenize the tool use prompt |
|
inputs = tokenizer.apply_chat_template( |
|
conversation, |
|
tools=tools, |
|
add_generation_prompt=True, |
|
return_dict=True, |
|
return_tensors="pt", |
|
) |
|
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto") |
|
|
|
inputs.to(model.device) |
|
outputs = model.generate(**inputs, max_new_tokens=1000) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
Note that, for reasons of space, this example does not show a complete cycle of calling a tool and adding the tool call and tool |
|
results to the chat history so that the model can use them in its next generation. For a full tool calling example, please |
|
see the [function calling guide](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling), |
|
and note that Mistral **does** use tool call IDs, so these must be included in your tool calls and tool results. They should be |
|
exactly 9 alphanumeric characters. |
|
|
|
> [!TIP] |
|
> Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3. |
|
|
|
## Limitations |
|
|
|
The Mistral Nemo Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. |
|
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to |
|
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. |
|
|
|
## The Mistral AI Team |
|
|
|
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall |
|
|
